WO2022160938A1 - Emergency help-seeking function triggering method and apparatus, terminal, and storage medium - Google Patents
Emergency help-seeking function triggering method and apparatus, terminal, and storage medium Download PDFInfo
- Publication number
- WO2022160938A1 WO2022160938A1 PCT/CN2021/135473 CN2021135473W WO2022160938A1 WO 2022160938 A1 WO2022160938 A1 WO 2022160938A1 CN 2021135473 W CN2021135473 W CN 2021135473W WO 2022160938 A1 WO2022160938 A1 WO 2022160938A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- audio data
- data
- human
- emergency
- condition
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000004044 response Effects 0.000 claims abstract description 61
- 230000001960 triggered effect Effects 0.000 claims abstract description 31
- 230000006870 function Effects 0.000 claims description 147
- 230000007613 environmental effect Effects 0.000 claims description 56
- 230000001755 vocal effect Effects 0.000 claims description 51
- 230000008451 emotion Effects 0.000 claims description 48
- 238000004891 communication Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 10
- 238000000926 separation method Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000008909 emotion recognition Effects 0.000 claims description 7
- 230000002996 emotional effect Effects 0.000 description 16
- 238000012545 processing Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 12
- 230000002159 abnormal effect Effects 0.000 description 9
- 238000012544 monitoring process Methods 0.000 description 8
- 239000008280 blood Substances 0.000 description 7
- 210000004369 blood Anatomy 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 6
- 229910052760 oxygen Inorganic materials 0.000 description 6
- 239000001301 oxygen Substances 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000013480 data collection Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 208000024172 Cardiovascular disease Diseases 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000036651 mood Effects 0.000 description 2
- 206010010071 Coma Diseases 0.000 description 1
- 102000001554 Hemoglobins Human genes 0.000 description 1
- 108010054147 Hemoglobins Proteins 0.000 description 1
- 206010036086 Polymenorrhoea Diseases 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 230000001976 improved effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004962 physiological condition Effects 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0453—Sensor means for detecting worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
- A61B5/6898—Portable consumer electronic devices, e.g. music players, telephones, tablet computers
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/7465—Arrangements for interactive communication between patient and care services, e.g. by using a telephone network
- A61B5/747—Arrangements for interactive communication between patient and care services, e.g. by using a telephone network in case of emergency, i.e. alerting emergency services
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0469—Presence detectors to detect unsafe condition, e.g. infrared sensor, microphone
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2560/00—Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
- A61B2560/02—Operational features
- A61B2560/0242—Operational features adapted to measure environmental factors, e.g. temperature, pollution
Definitions
- the embodiments of the present application relate to the technical field of terminals, and in particular, to a method, device, terminal, and storage medium for triggering an emergency help function.
- the emergency help function is used for external help when the safety of the user's life or property is threatened.
- the user usually needs to press a physical button on the terminal to trigger the emergency help function.
- the user may preset pressing the power button 5 times continuously as the triggering condition of the emergency help function.
- the embodiments of the present application provide a method, device, terminal and storage medium for triggering an emergency help function.
- the technical solution is as follows:
- an embodiment of the present application provides a method for triggering an emergency help function, and the method includes:
- audio collection is performed through a microphone to obtain audio data
- an emergency assistance function is triggered.
- an embodiment of the present application provides a triggering device for an emergency help function, and the device includes:
- the human body physiological data acquisition module is used to determine the human body physiological data based on the sensor data collected by the sensors in the wearable device;
- an audio data acquisition module configured to perform audio acquisition through a microphone in response to the human physiological data satisfying the first condition to obtain audio data
- a triggering module configured to trigger an emergency help function in response to the audio data meeting the second condition.
- a terminal comprising a processor and a memory; the memory stores at least one instruction for execution by the processor to implement the emergency as described in the above aspects The trigger method of the help function.
- a computer-readable storage medium stores at least one instruction for being executed by a processor to implement the method for triggering the emergency assistance function according to the above aspect.
- a computer program product or computer program comprising computer instructions stored in a computer-readable storage medium.
- the processor of the terminal reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the terminal executes the method for triggering the emergency help function provided in various optional implementation manners of the foregoing aspects.
- FIG. 1 is a schematic diagram of an implementation environment provided by an exemplary embodiment of the present application
- FIG. 2 is a flowchart of a method for triggering an emergency help function provided by an exemplary embodiment of the present application
- FIG. 3 is a flowchart of a method for triggering an emergency help function provided by another exemplary embodiment of the present application.
- FIG. 4 is a flowchart of a method for triggering an emergency help function provided by another exemplary embodiment of the present application.
- FIG. 5 is a flowchart of a method for triggering an emergency help function provided by another exemplary embodiment of the present application.
- FIG. 6 is a schematic diagram of the implementation of risk prompting by a wearable device provided by an embodiment of the present application.
- FIG. 7 is a structural block diagram of an apparatus for triggering an emergency help function provided by an exemplary embodiment of the present application.
- FIG. 8 shows a structural block diagram of a terminal provided by an exemplary embodiment of the present application.
- plural refers to two or more.
- “And/or”, which describes the association relationship of the associated objects, means that there can be three kinds of relationships, for example, A and/or B, which can mean that A exists alone, A and B exist at the same time, and B exists alone.
- the character “/” generally indicates that the associated objects are an "or" relationship.
- Wearable device refers to a portable product that can be worn on the body. Wearable device is not only a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. In use, a variety of functions can be achieved through software support and data interaction, connecting mobile phones to achieve interoperability, and continuously expanding new technologies around health monitoring, social communication, and audio-visual audio-visual functions. Wearable devices are represented by smart watches and smart bracelets. The rapid development of wireless technology has driven the maturity of the wearable ecosystem, making wearable devices enter the stage of rising, and there will be various forms of product derivatives in the market, such as Smart glasses, Augmented Reality (AR), Virtual Reality (VR), etc.
- AR Augmented Reality
- VR Virtual Reality
- the wearable device collects human physiological data, and analyzes the collected external audio data to determine whether the conditions for triggering the emergency help function are met. Trigger, in special circumstances, the automatic triggering of the emergency help function can be realized, and the timeliness of emergency help can be improved.
- audio collection is performed through a microphone to obtain audio data
- the emergency assistance function is triggered.
- an emergency help function including:
- Audio separation is performed on the audio data to obtain human voice audio data and ambient sound audio data;
- the emergency assistance function is triggered in response to the human voice recognition result and/or the ambient sound recognition result indicating that the audio data satisfies the second condition.
- identify the human voice audio data to obtain a voice recognition result including:
- Identify ambient sound audio data to obtain ambient sound identification results including:
- the environmental sound audio data is subjected to environmental recognition to obtain environmental information, and the environmental information is determined as the environmental sound recognition result, and the environmental information is used to represent the environmental type of the current environment.
- triggering an emergency help function including:
- the vocal emotion information indicating a preset emotion, and/or the keyword matching result indicating that the vocal text contains a preset keyword, and/or the environmental information indicating a quiet environment determine that the audio data satisfies the second condition, and trigger emergency help Function.
- an emergency help function is triggered, including:
- audio collection is performed through a microphone to obtain audio data, including:
- the human physiological data includes at least one of heart rate data and stress data;
- the fluctuation range includes at least one of a heart rate fluctuation range and a pressure fluctuation range.
- the method further includes:
- a risk prompt is performed
- an emergency help function including:
- an emergency help function is triggered, and the positive feedback is used to indicate that the human physiological data is normal.
- trigger the emergency help function including:
- the help message includes audio data and geographic location information.
- FIG. 1 shows a schematic diagram of an implementation environment provided by an exemplary embodiment of the present application.
- the implementation environment includes the wearable device 110 and the mobile terminal 120 .
- the wearable device 110 has the function of collecting human physiological data, which may be a device with the function of collecting human physiological data, such as a smart watch or a smart bracelet.
- the embodiment of the present application does not limit the specific device type of the wearable device 110 .
- the wearable device 110 has a mobile data communication capability, and can implement data communication and call functions without the aid of other devices.
- a wireless communication connection is established between the wearable device 110 and the mobile terminal 120, so as to realize data communication and call functions through the wireless communication connection, wherein the wireless communication connection may be a Bluetooth connection .
- the mobile terminal 120 is an electronic device with mobile data communication capability, which may be an electronic device such as a smart phone, a tablet computer, etc.
- the embodiment of the present application does not limit the specific device type of the mobile terminal 120 .
- the mobile terminal 120 judges whether the first condition is satisfied by analyzing the human physiological data collected by the wearable device 110, and when the judgment result of the human physiological data satisfies the first condition, the The microphone component collects external audio data, analyzes the audio data, and determines whether the audio data satisfies the second condition. When the judgment result of the audio data satisfies the second condition, it is determined that the user currently needs emergency assistance, thereby actively triggering the emergency assistance function.
- the analysis of human physiological data, the collection of audio data, and the analysis steps are all performed by the wearable device 110.
- the wearable device 110 triggers the Its own emergency help function, or trigger the emergency help function through the mobile terminal 120 .
- FIG. 2 is a flowchart of a method for triggering an emergency help function provided by an embodiment of the present application. The method includes:
- Step 201 Determine human physiological data based on sensor data collected by sensors in the wearable device.
- the wearable device collects sensor data through built-in sensors, analyzes the sensor data and determines the corresponding human physiological data.
- the process of obtaining human physiological data according to the sensor data can be performed by a wearable device or a bound mobile terminal.
- the wearable device has the function of analyzing sensor data, it can directly monitor human body data; when the wearable device does not have the function of analyzing sensor data, the sensor data can be sent to the bound mobile terminal through wireless Bluetooth or network. , processed by the mobile terminal to obtain various human physiological data.
- This embodiment is described by taking the wearable device determining human physiological data based on sensor data as an example.
- Wearable devices collect human physiological data in real time through sensors, and monitor changes in human physiological data.
- the collected human physiological data may be at least one of heart rate data, pressure data and blood oxygen concentration data.
- changes in the human physiological data include at least one of heart rate fluctuations, pressure fluctuations and blood oxygen concentration changes. A sort of.
- the heart rate data is obtained through the built-in heart rate sensor of the wearable device.
- the basic working principle is to use the difference in light transmittance caused by the pulsation of blood vessels in the human body to measure the pulse.
- the heart rate sensor collects the data, it is converted by a photoelectric converter.
- the basic working principle is to use near-infrared light of a specific wavelength as the incident light source to measure the light transmission intensity through human tissue, and calculate the hemoglobin concentration and blood oxygen saturation according to the measured light transmission intensity value.
- the monitoring of blood oxygen concentration plays an important role in the prediction of sudden disease.
- Step 202 in response to the human physiological data satisfying the first condition, audio collection is performed through a microphone to obtain audio data.
- the wearable device detects that the physiological data of the human body meets the first condition, that is, the monitored physiological data of the human body conforms to the physiological characteristics of the user in emergency situations, including that the physiological data of the human body exceeds or falls below the normal physiological index range, and the fluctuation range of the physiological data of the human body exceeds the normal range. range, abnormal changes in human physiological data, etc.
- the terminal collects external audio data through a microphone. Only when the monitored human physiological data meets the first condition, will the microphone be triggered to perform audio collection to save power consumption.
- the monitored human physiological data does not meet the first condition, that is, when all human physiological data Trigger the microphone to collect audio data.
- Collecting external audio data through a microphone may include at least one of the following situations:
- the wearable device is provided with a microphone assembly.
- the wearable device detects that the physiological data of the human body conforms to the physiological characteristics of the user in emergency situations, the external audio data is collected through the microphone component, and the duration of the audio data may be a preset duration or a user-adjusted duration.
- the wearable device does not have a microphone component, and the mobile terminal has the function of collecting audio data.
- the mobile terminal detects that the physiological data of the human body conforms to the physiological characteristics of the user's human body in an emergency, the microphone is turned on to collect audio data.
- the wearable device when the wearable device does not have a microphone component, when the wearable device detects that the physiological data of the human body conforms to the physiological characteristics of the user in an emergency, it sends an audio data collection instruction to the mobile terminal, and the corresponding mobile terminal receives the audio data collection. After the command, turn on the microphone to collect audio data.
- the wearable device sends the collected human physiological data to the mobile terminal, and the mobile terminal makes a judgment based on the human physiological data, and when it is determined that the human physiological data conforms to the human physiological characteristics in an emergency, the microphone is turned on to collect audio data. .
- Step 203 in response to the audio data meeting the second condition, trigger an emergency help function.
- the terminal After collecting audio data by using a microphone, the terminal processes and analyzes the audio data.
- the analysis result of the audio data satisfies the second condition, that is, the processing result of the audio data satisfies the sound characteristics in emergency situations, it is determined that the user currently needs urgent Ask for help, trigger the emergency help function, and the operation of triggering the emergency help function is performed by the wearable device or the mobile terminal.
- the wearable device when the processing and analysis of the audio data is performed by the wearable device, that is to say, the wearable device analyzes that the user needs emergency help, the wearable device will give priority to triggering the emergency help function; After analyzing that the user needs emergency help, the terminal will give priority to triggering the emergency help function, which can improve the timeliness of triggering the emergency help function.
- Processing the collected audio data includes at least one of the following situations:
- the wearable device When the wearable device has the audio data processing and analysis capabilities, the wearable device directly processes and analyzes the collected audio data, and judges whether the second condition is satisfied according to the result of the data processing.
- the wearable device sends the collected audio data to the bound mobile terminal through wireless Bluetooth or the network, and processes and analyzes the audio data through the mobile terminal to determine the audio data. whether the second condition is met.
- the mobile terminal bound to the wearable device determines whether the first and second conditions are met.
- the mobile terminal receives the wearable device When the sent human physiological data satisfies the first condition, audio data is collected through the microphone assembly, and the collected audio data is analyzed and processed to determine whether the second condition is met.
- the terminal After the emergency help function is triggered, the terminal initiates emergency help to the emergency contact in a preset manner, and the method for initiating emergency help may include at least one of the following situations:
- the wearable device has the function of voice calling.
- the wearable device dials the emergency contact through the built-in voice call component to initiate emergency communication, and seeks help from the other party.
- the emergency contact can be a preset family member or friend, and also The emergency contact can be set as the public security alarm system or emergency center.
- the wearable device has the function of sending information.
- the help information can be voice information or text information set in advance; on the premise that the wearable device has been connected to a medical institution, it can Send help information directly to designated medical institutions to provide targeted assistance.
- Wearable devices do not have call function or voice call function.
- the method for triggering the emergency help function is based on the real-time monitoring of human physiological data based on the sensors in the wearable device.
- the monitored human physiological data meets the first condition, that is, the human physiological data is abnormal.
- judging that the user may be in an emergency situation so as to collect external audio data through the microphone, and analyze the audio data, and then when the audio data meets the second condition, determine that the user is in an emergency state, and trigger the emergency help function;
- the method provided by the example based on human physiological data and audio data for emergency help state identification, can realize the automatic triggering of the emergency help function when the user cannot manually trigger the emergency help function, and improve the triggering timeliness of the emergency help function; at the same time, Taking human physiological data and audio data together as triggering basis helps to reduce the probability of false triggering and improve the accuracy of triggering timing.
- FIG. 3 is a flowchart of a method for triggering an emergency help function provided by another exemplary embodiment of the present application, and the method includes:
- Step 301 Determine human physiological data based on sensor data collected by sensors in the wearable device.
- the wearable device can be a device with the function of monitoring human physiological data, such as a smart watch or a wristband. Users can monitor human physiological data in real time through the wearable device. For details, please refer to the steps 201, the embodiments of the present application will not be described in detail again.
- the human physiological data determined by the terminal includes at least one of heart rate data and stress data.
- Step 302 Determine the fluctuation range of the human physiological data based on the continuous human physiological data.
- the terminal determines the fluctuation range of the human physiological data based on the continuously determined human physiological data, so as to determine whether the human physiological data meets the first condition based on the fluctuation range.
- the terminal acquires human physiological data at n consecutive times, and calculates the data variance of the human physiological data at n times, so as to determine the data variance as the fluctuation range of the human physiological data.
- the fluctuation range is the heart rate fluctuation range
- the fluctuation range is the pressure fluctuation range.
- the terminal may also determine the fluctuation range according to parameters such as the peak value and standard deviation of the human physiological data, which is not limited in this embodiment of the present application.
- the terminal detects whether the fluctuation range of the human physiological data is greater than the amplitude threshold. If it is greater than the amplitude threshold, it is determined that the human physiological data conforms to the physiological characteristics of the emergency help state, and step 303 is executed; Physiological characteristics of the state, and continue to monitor human physiological data.
- the amplitude threshold may be preset, or calculated based on the normal human physiological data of the user.
- different amplitude thresholds may be set according to different human physiological data.
- Step 303 in response to the fluctuation amplitude being greater than the amplitude threshold, it is determined that the physiological data of the human body meets the first condition, and audio is collected through a microphone to obtain audio data.
- the terminal determines that the human physiological data meets the first condition, thereby triggering the microphone to collect audio data.
- the preset time may be 30s.
- the terminal determines that the human physiological data meets the first condition, thereby triggering the microphone to collect audio data.
- the user may preset to focus on monitoring one or more kinds of human physiological data, and then when the fluctuation range of the human physiological data exceeds the amplitude threshold, the terminal determines that the human physiological data meets the first condition.
- the terminal determines that the human physiological data meets the first condition.
- the wearable device when the wearable device detects that the fluctuation range of the current human physiological data exceeds the amplitude threshold, the mobile terminal or wearable device can send out vibrations or ringing as a reminder.
- the wearable device turns on the microphone to collect the external audio data and starts timing, and the duration of the microphone to collect the external audio may be a preset duration or a duration set in advance by the user, and when the timing duration reaches the set duration, Stop collecting external audio data through the microphone, and the collected audio data is stored in the wearable device.
- the wearable device has limited storage space, and the wearable device can transmit the collected historical audio data to the bound mobile terminal through Bluetooth or the network.
- the wearable device can periodically delete the historical audio data, so as to avoid the storage space being occupied by the historical audio data, which makes it impossible to collect the current audio data in time.
- Step 304 Perform audio separation on the audio data to obtain human voice audio data and ambient sound audio data.
- the audio data collected through the microphone may include human voices, noisy ambient sounds, and interference noise. Each sound corresponds to a different frequency band and has different characteristics. It needs to be filtered, and the human voice and ambient sound may contain important information that can judge the user's current emergency state. Therefore, it is also necessary to separate the human voice audio and ambient sound audio in the collected audio data. and human voices are judged separately.
- the terminal filters out the interference noise in the collected audio data through a filtering algorithm, and then separates the human voice and ambient sound in the audio data using different algorithms to obtain the human voice audio data. and ambient sound audio data.
- the convolutional neural network can be used to convert the audio data filtered out of the interference noise into a spectrogram.
- Neural Network, CNN recognizes the spectrogram, recognizes the spectrogram information of the human voice, and then converts the new spectrogram obtained from the recognition into audio, and finally generates pure human voice audio data; further, the terminal is based on the audio data and human voice. The sound and audio data are separated to obtain ambient sound audio data.
- the embodiments of the present application do not limit the specific manner used for audio separation.
- Step 305 Identify the human voice audio data to obtain a human voice recognition result.
- the voice recognition result can reflect whether the user's situation is in danger to a certain extent. .
- the terminal amplifies and processes the separated vocal audio through the vocal enhancement technology, so as to facilitate further processing of the audio information, and the vocal audio data can be identified by comparing the processed vocal audio with the pre-recorded user audio. , confirming whether the human voice in the collected audio data is the user's own voice, so as to judge the user's state; or, by transforming the human voice audio into human voice text, making a judgment based on the content of the text information.
- step 305 may include the following steps.
- Step 305A Perform emotion recognition on the vocal audio data to obtain vocal emotion information.
- the terminal processes and analyzes the vocal audio data, identifies the current emotional state of the user, and obtains vocal emotional information.
- the vocal emotional information can reflect the user's true emotions in an emergency state to a certain extent.
- a speech emotion recognition algorithm (Speech Emotion Recognition, SER) based on deep learning can be used to identify "anger”, “happy”, “fear” and “sadness” expressed in human voice audio Emotions, each corresponding to the user's emotional state.
- SER speech Emotion Recognition
- the identified vocal emotion is "happy”
- the corresponding user may experience a happy event, which may lead to large fluctuations in human physiological data, and no help is needed
- the identified vocal emotion is "fear”
- the user may In the event of a personal threat or sudden illness, emergency assistance is required.
- it will also lead to changes in human physiological data and emotions. Therefore, it is impossible to make accurate judgments simply by recognizing human voice emotions.
- Step 305B performing audio-text conversion on the human voice audio data to obtain human voice text; performing keyword matching on the human voice text to obtain a keyword matching result, and the keyword matching result is used to indicate whether the human voice text contains preset keywords .
- the terminal can also perform audio-text conversion on the human voice audio data to obtain the human voice text, so as to determine whether the voice text contains information related to emergency help. keyword to determine whether the user is currently in an emergency state.
- audio-to-text conversion is performed on the basis of the acquired human voice audio data, and the acoustic features in the human voice audio data are extracted by using an acoustic model and a language model, and the human voice audio is further converted into human voice audio through an algorithm.
- Acoustic text such as using automatic speech recognition technology (Automatic Speech Recognition, ASR) to convert real-time input speech signal into text output.
- ASR Automatic Speech Recognition
- the terminal needs to recognize the human voice text, and the recognition of the human voice text can assist in judging the emotional state of the user to a certain extent.
- Match the vocal text with preset keywords to determine whether the vocal text contains preset keywords.
- the preset keywords can be words related to emergency help or code words set by the user. As long as the code words are recognized, it represents the user Threatened by a person, the emergency help function is triggered immediately.
- one or more preset keywords are matched during the human-voice-text matching process, it is determined that the user may currently be threatened personally.
- Step 305C determining the human voice emotion information and/or the keyword matching result as the human voice recognition result.
- the terminal determines at least one of the recognized human voice emotion information and the keyword matching result as the human voice recognition result.
- the server determines the recognized item as the human voice recognition result; if both the human voice emotion information and the keyword matching result are recognized at the same time, the server determines both as the human voice recognition result.
- any one of the vocal emotion information or the keyword matching result determines that the accuracy of the vocal recognition result is low.
- the vocal emotion information and the keyword can be matched.
- the results are jointly determined as the human voice recognition result, and the recognized keywords and the vocal emotion information are matched, and the human voice recognition result is determined by the corresponding relationship between the vocal emotion information and the keywords; if the recognized keywords and the vocal emotion information are Corresponding relationship, it is determined that the human voice recognition result indicates that the user is currently in a dangerous state or a safe state.
- the preset keywords may be set in a relationship corresponding to the emotional information of the human voice.
- the corresponding preset keywords can be set to words such as “very happy”, “in a good mood” or “very good”, indicating that the user may be too excited by happy things, which may lead to the change of human physiological data.
- the fluctuation range exceeds the threshold, and there is no personal threat; when the voice emotion is "fear”, the corresponding preset keywords can be set to "shut up”, “kill you”, “help” and other words, indicating that the user is in danger state.
- Step 306 Identify the ambient sound audio data to obtain an ambient sound identification result.
- this step may include step 306A.
- Step 306A Perform environmental recognition on the audio data of the environmental sound to obtain environmental information, and determine the environmental information as the environmental sound recognition result, where the environmental information is used to represent the environmental type of the current environment.
- the ambient sound recognition result may be obtained by matching the collected ambient sound audio with the preset ambient audio.
- the preset ambient audio may be audio collected in a noisy environment or a quiet environment, or may be audio collected in some specific environments, such as a theater environment or a sports field environment, etc.
- the current environment information is determined according to the matching content.
- the result of matching is a cinema environment or a noisy environment, it indicates that the user is currently watching a movie or in a lively environment, and there is no need for emergency help.
- the matching result is a silent environment, it indicates that the user currently needs emergency help.
- the terminal performs decibel value detection on the acquired ambient sound and audio data, and determines whether the user's current environment is noisy or quiet according to the level of the decibel value.
- the decibel value is higher than the threshold, the environment recognition result is determined as The user is in a noisy environment, and when the decibel value is lower than the threshold, the environment recognition result determines that the user is in a quiet environment.
- Step 307 in response to the human voice recognition result and/or the ambient sound recognition result indicating that the audio data satisfies the second condition, trigger an emergency help function.
- the terminal determines whether the audio data satisfies the second condition based on at least one of the human voice recognition result and the environmental sound recognition result, and triggers an emergency help function when the audio data satisfies the second condition.
- this step Step 307A may be included.
- Step 307A when the vocal emotion information indicates a preset emotion, and/or the keyword matching result indicates that the vocal text contains a preset keyword, and/or the environmental information indicates that it is in a quiet environment, it is determined that the audio data satisfies the second condition, Trigger the emergency help function.
- the terminal uses at least one of the identified human voice emotional information, keyword matching results and environmental information as the judgment basis for judging whether to trigger the emergency help function.
- the judgment result meets the second condition
- the emergency help function is triggered.
- the judgment result When the second condition is not met, the emergency help function is not triggered.
- any one, any two or three of the human voice emotion information, the keyword matching result and the environmental information may be used as the judgment basis.
- the probability of triggering the emergency help function with any one of them as the judgment basis is the highest, but at the same time, the possibility of false triggering is also the greatest. The possibility also becomes smaller.
- the probability of triggering the emergency help function is the smallest, but the possibility of false triggering is the lowest. The following descriptions are given by taking any one, any two, and three as the judgment basis.
- the emotional information of the human voice is used as the judgment basis, and when the recognized emotional emotional information of the human voice is the preset "fear" emotion, it is determined that the user may currently be threatened by a person causing a change in the emotion, thereby triggering an emergency
- the identified voice emotion information is a preset "happy" emotion or does not indicate a preset emotion, the second condition is not satisfied, that is, the emergency help function is not triggered.
- the keyword matching result indicates that the preset keyword is included, it indicates that the user is in an emergency state, and then the emergency help function is triggered.
- the matching result indicates that the preset keyword is not included, it is determined that the user is not in danger, and the emergency help function is not triggered.
- the emergency help function when judging whether the emergency help function needs to be triggered based on environmental information, when the identified environmental information is a noisy environment or the decibel value exceeds the set threshold, it indicates that the user is not in an emergency state, and when the identified environment information is a noisy environment or the decibel value exceeds the set threshold When the environmental information is a silent environment or the decibel value is lower than the set threshold, it indicates that the user is in an emergency state, that is, the emergency help function is triggered.
- the vocal emotion information and the keyword matching result are used as the judgment basis, when the vocal emotion information indicates a preset emotion, and the keyword matching result contains a preset keyword, it indicates that the user is currently in an emergency state, and the satisfaction is satisfied.
- the second condition is to trigger the emergency help function.
- any one or both of the emotional information of the human voice, the keyword matching results and the environmental information can be used as the basis for judging whether to trigger the emergency help function, but there may be misjudgments in some special cases. For example, when a user runs in a quiet environment or does other strenuous exercise, only making judgments based on environmental information may cause misjudgments.
- vocal emotion information and keyword matching results may also cause misjudgment in some special cases, such as watching a horror movie, due to the tense atmosphere and playing sounds, the user's human physiological data will be temporarily abnormal, and may The preset keywords will be matched, and the emergency help function will be triggered by mistake. The actual user does not need to trigger the emergency help function. Therefore, it is also impossible to make an accurate judgment by relying on the emotional information of the human voice and the keyword matching results.
- a judgment basis can also be made on the basis of the human voice recognition result combined with environmental information.
- Set the mood, and the keyword matching result indicates that the preset keyword is included, and when the ambient sound recognition result indicates a silent environment, it is determined that the collected audio data satisfies the second condition, that is, it is determined that the user is in an emergency help state, thereby automatically triggering the emergency help function. Get help.
- a wearable device having a call function, a message sending function, and a positioning function is used as an example for description.
- the wearable device determines that the audio data meets the second condition, it determines that the user is in an emergency state, and triggers the wearable device to send at least one emergency contact a help message or initiate an emergency communication, where the help message includes the collected audio data and
- the current geographic location information and the content of the help information may be preset text information or voice information.
- targeted help is provided according to the content of the help information.
- the emergency contact can be a preset family member or friend.
- the emergency contact can be set as the public security alarm system or emergency center.
- the method of the emergency help function can be determined by combining the previous human voice recognition results and human physiological data.
- the public security alarm system will be given priority.
- Initiate help if it is determined that the user has a sudden illness based on the results of human voice recognition, the emergency center will be prioritized for help.
- the user may fall into a coma due to a sudden illness in the middle of the night, and the audio data collected through the microphone may not be able to detect human voice emotional information and keywords. Danger to life.
- the environmental information indicates that it is in a quiet environment
- further judgment can be made by obtaining the current time information.
- the current time is obtained, and if the current time is within a preset time period, an emergency help function is triggered.
- the terminal detects whether the acquired current time belongs to the preset time period, and if it belongs to the preset time period, it determines that it is in an emergency help state, and triggers the emergency help function; if it does not belong to the preset time period, it determines that it is not in the emergency help state, and Continue to monitor.
- the preset time period may be automatically set based on the user's disease condition, for example, when the user suffers from cardiovascular disease, the preset time period may be a frequent period of cardiovascular disease, such as the early morning time period and the early morning time period; The set time period may also be set by the user, which is not limited in this embodiment.
- the built-in sensor of the wearable device to monitor the human physiological data in real time, when the fluctuation range of the human physiological data exceeds the amplitude threshold, it is judged that the user may be in a dangerous state, so that the external audio data is collected through the microphone for further judgment to avoid Long-term audio data collection and analysis results in increased terminal power consumption.
- the corresponding human voice feature information and ambient sound feature information are extracted from the human voice audio data and the ambient sound audio data.
- the human voice feature information and the ambient sound feature information determine whether the user is in an emergency help state, which helps to improve the accuracy of the trigger timing of the subsequent emergency help function.
- the terminal may give a prompt while collecting and analyzing audio data.
- the terminal determines that the user is in an emergency state and actively triggers emergency assistance. Function. Conversely, if positive feedback to the prompt is received, it is determined that the user is not in an emergency state. Exemplary embodiments are used for description below.
- FIG. 5 is a flowchart of a method for triggering an emergency help function provided by another exemplary embodiment of the present application, and the method includes:
- Step 501 Determine human physiological data based on sensor data collected by sensors in the wearable device.
- step 201 For the implementation of this step, reference may be made to step 201, and details are not described herein again in this embodiment.
- Step 502 in response to the human physiological data meeting the first condition, collect audio data through a microphone and perform a risk prompt.
- the terminal collects audio data through a microphone, issues a risk prompt at the same time, and receives feedback from the user.
- the user's feedback includes positive feedback and negative feedback, wherein, positive feedback indicates abnormal human physiological data caused by non-emergency help (no risk); negative feedback indicates abnormal human physiological data caused by emergency help (risk exists) ).
- the wearable device when the wearable device detects that the human heart rate or the pressure value fluctuates more than the amplitude threshold in a short period of time, the wearable device will alert the human body that there is an abnormality in the human physiological data by emitting vibration or sound.
- the user can give positive feedback by clicking the physical button.
- the risk prompt may also be a screen-on prompt, and prompt information is displayed on the interface of the wearable device.
- an information prompt box 611 is displayed on the interface to remind the user to give feedback.
- the information prompt box 611 includes the abnormal human physiological data 612 of the user currently.
- the user determines whether it is a misjudgment reminder by manually clicking.
- the display duration of the information prompt box 611 is a preset duration. When the user makes positive feedback (such as clicking the normal button) within the preset duration, it indicates that the current user is in good physical condition and stops collecting audio data; the wearable device 610 is in the preset duration. When negative feedback is received (such as clicking the alarm button) or no feedback is received (such as no click operation on any button is received within the display time of the information prompt box), it indicates that the user is currently in an emergency state.
- the wearable device 610 directly triggers the emergency help function.
- the wearable device 610 determines whether the emergency help function needs to be triggered based on the recognition result of the audio data.
- Step 503 in response to the audio data meeting the second condition and no positive feedback on the risk prompt being received, an emergency help function is triggered, and the positive feedback is used to indicate that the human physiological data is normal.
- the terminal determines that the user is in an emergency Help state, thus triggering the emergency help function.
- the preset duration may be set by the user, or the default setting may be adopted, and the preset duration may be 15s.
- the wearable device 610 displays the information prompt box 611, if the click operation on the “normal” button or the “alarm” button is not received within 20s, the wearable device 610 will send an The mobile terminal 620 sends the trigger instruction, and after receiving the trigger instruction, the mobile terminal 620 triggers the emergency help function (sends a preset short message to the emergency contact son).
- the terminal when the monitored physiological data of the human body is abnormal, the terminal performs a risk prompt to remind the user to give corresponding feedback; if it receives positive feedback from the user, it indicates that the emergency help function does not need to be triggered; if it receives negative feedback or does not receive Feedback, then by analyzing the collected audio data, it is further determined whether the triggering conditions of the emergency help function are met, and the probability of false triggering of the emergency help function is reduced.
- FIG. 7 is a structural block diagram of an apparatus for triggering an emergency help function provided by an exemplary embodiment of the present application, and the apparatus includes:
- An audio data collection module 702 configured to perform audio collection through a microphone in response to the human physiological data satisfying the first condition to obtain audio data
- the triggering module 703 is configured to trigger the emergency help function in response to the audio data meeting the second condition.
- the trigger module 703 includes:
- the audio separation unit is used for audio separation of audio data to obtain human voice audio data and ambient sound audio data;
- the human voice recognition unit is used to identify the human voice audio data to obtain the human voice recognition result
- the environmental sound recognition unit is used to recognize the environmental sound audio data to obtain the environmental sound recognition result
- a triggering unit configured to trigger the emergency help function in response to the human voice recognition result and/or the ambient sound recognition result indicating that the audio data satisfies the second condition.
- voice recognition unit for:
- ambient sound recognition unit for:
- the environmental sound audio data is subjected to environmental recognition to obtain environmental information, and the environmental information is determined as the environmental sound recognition result, and the environmental information is used to represent the environmental type of the current environment.
- the trigger unit is also used to:
- the vocal emotion information indicating a preset emotion, and/or the keyword matching result indicating that the vocal text contains a preset keyword, and/or the environment information indicating a quiet environment determine that the audio data satisfies the second condition, and trigger an emergency Help function.
- the trigger unit is also used to:
- the audio data collection module 702 includes:
- the fluctuation range determination unit is used for determining the fluctuation range of the human physiological data based on the continuous human physiological data
- the audio collection unit is used for determining that the physiological data of the human body meets the first condition in response to the fluctuation amplitude being greater than the amplitude threshold, and performing audio collection through a microphone to obtain audio data.
- the human physiological data includes at least one of heart rate data and stress data;
- the fluctuation range includes at least one of a heart rate fluctuation range and a pressure fluctuation range.
- the device further includes:
- a risk prompting module configured to perform risk prompting in response to the human physiological data satisfying the first condition
- the triggering module 703 is further configured to:
- an emergency help function is triggered, and the positive feedback is used to indicate that the human physiological data is normal.
- the triggering module 703 is further configured to:
- the help message includes audio data and geographic location information.
- the method for triggering the emergency help function is based on the real-time monitoring of human physiological data based on the sensors in the wearable device.
- the monitored human physiological data meets the first condition, that is, the human physiological data is abnormal.
- judging that the user may be in an emergency situation so as to collect external audio data through the microphone, and analyze the audio data, and then when the audio data meets the second condition, determine that the user is in an emergency state of assistance, and trigger the emergency assistance function;
- the method provided by the example based on human physiological data and audio data for emergency help state identification, can realize the automatic triggering of the emergency help function when the user cannot manually trigger the emergency help function, and improve the triggering timeliness of the emergency help function; at the same time, Using human physiological data and audio data as the trigger basis can help reduce the probability of false triggering and improve the accuracy of trigger timing.
- FIG. 8 shows a structural block diagram of a terminal provided by an exemplary embodiment of the present application.
- the terminal 800 may be a smart phone, a tablet computer, a wearable device, or the like.
- the terminal 800 in this application may include one or more of the following components: a processor 810 and a memory 820 .
- Processor 810 may include one or more processing cores.
- the processor 810 uses various interfaces and lines to connect various parts in the entire terminal 800, and executes the terminal by running or executing the instructions, programs, code sets or instruction sets stored in the memory 820, and calling the data stored in the memory 820. various functions and processing data.
- the processor 810 may adopt at least one of digital signal processing (Digital Signal Processing, DSP), field-programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA).
- DSP Digital Signal Processing
- FPGA Field-Programmable Gate Array
- PLA programmable logic array
- the processor 810 may integrate one or more of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU), a neural network processor (Neural-network Processing Unit, NPU), and a modem, etc.
- a central processing unit Central Processing Unit, CPU
- a graphics processor Graphics Processing Unit, GPU
- a neural network processor Neural-network Processing Unit, NPU
- a modem etc.
- the CPU mainly processes the operating system, user interface, and application programs
- the GPU is used for rendering and drawing the content that needs to be displayed on the touch screen 830
- the NPU is used for implementing artificial intelligence (Artificial Intelligence, AI) functions
- the modem is used for Handle wireless communications. It can be understood that, the above-mentioned modem may not be integrated into the processor 810, but is implemented by a single chip.
- the memory 820 may include a random access memory (Random Access Memory, RAM), or may include a read-only memory (Read-Only Memory, ROM).
- the memory 820 includes a non-transitory computer-readable storage medium.
- Memory 820 may be used to store instructions, programs, codes, sets of codes, or sets of instructions.
- the memory 820 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), Instructions and the like for implementing the following various method embodiments; the storage data area may store data (such as audio data, phone book) and the like created according to the use of the terminal 800 .
- the terminal 800 may further include a sensor 830 for monitoring human physiological conditions, the sensor 830 is used to collect sensor data, and send the sensor data to the processor 810, and the processor 810 obtains the user's information based on the sensor data.
- Human Physiological Data may include a heart rate sensor, a blood oxygen sensor, a skin conductance sensor, a skin temperature sensor, and the like.
- the terminal 800 may further include a microphone 840, and the microphone 840 is used to collect external audio data, and send the audio data to the processor 810, and the processor 810 analyzes and processes the audio data.
- the structure of the terminal 800 shown in the above drawings does not constitute a limitation on the terminal 800, and the terminal may include more or less components than those shown in the drawings, or a combination of some components, or a different arrangement of components.
- the terminal 800 further includes components such as a display screen, a radio frequency circuit, a wireless fidelity (Wireless Fidelity, WiFi) component, a power supply, and a Bluetooth component, which will not be repeated here.
- Embodiments of the present application further provide a computer-readable storage medium, where at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement the method for triggering the emergency help function described in the above embodiments .
- Embodiments of the present application provide yet another computer program product or computer program, where the computer program product or computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium.
- the processor of the terminal reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the terminal executes the method for triggering the emergency help function provided in various optional implementation manners of the foregoing aspects.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Multimedia (AREA)
- Pathology (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physiology (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Cardiology (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Psychiatry (AREA)
- Pulmonology (AREA)
- Signal Processing (AREA)
- Gerontology & Geriatric Medicine (AREA)
- General Physics & Mathematics (AREA)
- Hospice & Palliative Care (AREA)
- Child & Adolescent Psychology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Emergency Medicine (AREA)
- Nursing (AREA)
- Critical Care (AREA)
- Physical Education & Sports Medicine (AREA)
- Artificial Intelligence (AREA)
- Alarm Systems (AREA)
Abstract
An emergency help-seeking function triggering method and apparatus, a terminal, and a storage medium, relating to the technical field of terminals. The method comprises: determining human body physiological data on the basis of sensor data acquired by a sensor in a wearable device (201); in response to the human body physiological data satisfying a first condition, performing audio acquisition by means of a microphone to obtain audio data (202); and in response to the audio data satisfying a second condition, triggering an emergency help-seeking function (203). By using the emergency help-seeking function triggering method, an emergency help-seeking function can be automatically triggered when a user cannot manually trigger the emergency help-seeking function.
Description
本申请要求于2021年01月28日提交的申请号为202110118932.6、发明名称为“紧急求助功能的触发方法、装置、终端及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。This application claims the priority of the Chinese patent application with the application number 202110118932.6, filed on January 28, 2021, and the invention titled "Method, Device, Terminal and Storage Medium for Triggering Emergency Help Function", the entire contents of which are incorporated by reference in in this application.
本申请实施例涉及终端技术领域,特别涉及一种紧急求助功能的触发方法、装置、终端及存储介质。The embodiments of the present application relate to the technical field of terminals, and in particular, to a method, device, terminal, and storage medium for triggering an emergency help function.
紧急求助功能作为终端中的一种常见功能,用于在用户生命或财产安全受到威胁时进行对外求助。As a common function in the terminal, the emergency help function is used for external help when the safety of the user's life or property is threatened.
相关技术中,用户通常需要按压终端上的实体按键以触发紧急求助功能。比如,用户可以预先设置连续按压5次电源键作为紧急求助功能的触发条件。In the related art, the user usually needs to press a physical button on the terminal to trigger the emergency help function. For example, the user may preset pressing the power button 5 times continuously as the triggering condition of the emergency help function.
发明内容SUMMARY OF THE INVENTION
本申请实施例提供了一种紧急求助功能的触发方法、装置、终端及存储介质。所述技术方案如下:The embodiments of the present application provide a method, device, terminal and storage medium for triggering an emergency help function. The technical solution is as follows:
一方面,本申请实施例提供了一种紧急求助功能的触发方法,所述方法包括:On the one hand, an embodiment of the present application provides a method for triggering an emergency help function, and the method includes:
基于可穿戴式设备中传感器采集到的传感器数据确定人体生理数据;Determine human physiological data based on sensor data collected by sensors in the wearable device;
响应于所述人体生理数据满足第一条件,通过麦克风进行音频采集,得到音频数据;In response to the human physiological data meeting the first condition, audio collection is performed through a microphone to obtain audio data;
响应于所述音频数据满足第二条件,触发紧急求助功能。In response to the audio data satisfying the second condition, an emergency assistance function is triggered.
另一方面,本申请实施例提供了一种紧急求助功能的触发装置,所述装置包括:On the other hand, an embodiment of the present application provides a triggering device for an emergency help function, and the device includes:
人体生理数据采集模块,用于基于可穿戴式设备中传感器采集到的传感器数据确定人体生理数据;The human body physiological data acquisition module is used to determine the human body physiological data based on the sensor data collected by the sensors in the wearable device;
音频数据采集模块,用于响应于所述人体生理数据满足第一条件,通过麦克风进行音频采集,得到音频数据;an audio data acquisition module, configured to perform audio acquisition through a microphone in response to the human physiological data satisfying the first condition to obtain audio data;
触发模块,用于响应于所述音频数据满足第二条件,触发紧急求助功能。A triggering module, configured to trigger an emergency help function in response to the audio data meeting the second condition.
另一方面,提供了一种终端,所述终端包括处理器和存储器;所述存储器存储有至少一条指令,所述至少一条指令用于被所述处理器执行以实现如上述方面所述的紧急求助功能的触发方法。In another aspect, a terminal is provided, the terminal comprising a processor and a memory; the memory stores at least one instruction for execution by the processor to implement the emergency as described in the above aspects The trigger method of the help function.
另一方面,提供了一种计算机可读存储介质,所述存储介质存储有至少一条指令,所述至少一条指令用于被处理器执行以实现如上述方面所述的紧急求助功能的触发方法。In another aspect, a computer-readable storage medium is provided, the storage medium stores at least one instruction for being executed by a processor to implement the method for triggering the emergency assistance function according to the above aspect.
另一方面,提供了一种计算机程序产品或计算机程序,该计算机程序产品或计算机程序包括计算机指令,该计算机指令存储在计算机可读存储介质中。终端的处理器从计算机可读存储介质读取该计算机指令,处理器执行该计算机指令,使得该终端执行上述方面的各种可选实现方式中提供的紧急求助功能的触发方法。In another aspect, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. The processor of the terminal reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the terminal executes the method for triggering the emergency help function provided in various optional implementation manners of the foregoing aspects.
图1是本申请一个示例性实施例提供的实施环境的示意图;FIG. 1 is a schematic diagram of an implementation environment provided by an exemplary embodiment of the present application;
图2是本申请一个示例性实施例提供的紧急求助功能的触发方法的流程图;2 is a flowchart of a method for triggering an emergency help function provided by an exemplary embodiment of the present application;
图3是本申请另一个示例性实施例提供的紧急求助功能的触发方法的流程图;3 is a flowchart of a method for triggering an emergency help function provided by another exemplary embodiment of the present application;
图4是本申请另一个示例性实施例提供的紧急求助功能的触发方法的流程图;4 is a flowchart of a method for triggering an emergency help function provided by another exemplary embodiment of the present application;
图5是本申请另一个示例性实施例提供的紧急求助功能的触发方法的流程图;5 is a flowchart of a method for triggering an emergency help function provided by another exemplary embodiment of the present application;
图6是本申请一个实施性实施例提供的可穿戴式设备进行风险提示的实施示意图;FIG. 6 is a schematic diagram of the implementation of risk prompting by a wearable device provided by an embodiment of the present application;
图7是本申请一个示例性实施例提供的紧急求助功能的触发装置的结构框图;7 is a structural block diagram of an apparatus for triggering an emergency help function provided by an exemplary embodiment of the present application;
图8示出了本申请一个示例性实施例提供的终端的结构框图。FIG. 8 shows a structural block diagram of a terminal provided by an exemplary embodiment of the present application.
为使本申请的目的、技术方案和优点更加清楚,下面将结合附图对本申请实施方式作进一步地详细描述。In order to make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.
在本文中提及的“多个”是指两个或两个以上。“和/或”,描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。As used herein, "plurality" refers to two or more. "And/or", which describes the association relationship of the associated objects, means that there can be three kinds of relationships, for example, A and/or B, which can mean that A exists alone, A and B exist at the same time, and B exists alone. The character "/" generally indicates that the associated objects are an "or" relationship.
为了方便理解,下面对本申请实施例中涉及的名词进行说明:For the convenience of understanding, the terms involved in the embodiments of the present application are described below:
可穿戴式设备:可穿戴式设备是指能穿戴在身上的一种便携式产品,可穿戴式设备不仅仅是一种硬件设备,更是通过软件支持以及数据交互、云端交互实现强大的功能。在使用中可通过软件支持和数据交互实现多种功能,以连接手机实现互通,围绕着健康监测、社交通信、视听影音为主要功能不断拓展新的技术。可穿戴式设备以智能手表和智能手环为代表,无线技术的高速发展带动了可穿戴生态的成熟,使可穿戴式设备进入崛起的阶段,市场上将会有各种形态的产品衍生,如智能眼镜、增强现实技术(Augmented Reality,AR)、虚拟现实技术(Virtual Reality,VR)等。Wearable device: Wearable device refers to a portable product that can be worn on the body. Wearable device is not only a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. In use, a variety of functions can be achieved through software support and data interaction, connecting mobile phones to achieve interoperability, and continuously expanding new technologies around health monitoring, social communication, and audio-visual audio-visual functions. Wearable devices are represented by smart watches and smart bracelets. The rapid development of wireless technology has driven the maturity of the wearable ecosystem, making wearable devices enter the stage of rising, and there will be various forms of product derivatives in the market, such as Smart glasses, Augmented Reality (AR), Virtual Reality (VR), etc.
相关技术中,当用户在某种突发事件下需要紧急求助时,只能通过手动点击实体按键或通过语音输入指令的方式触发设备发送求助信息,在某些特殊情 况下,如遭遇歹徒威胁或突发疾病无法行动的情况下,用户往往无法主动触发紧急求助功能。In the related art, when a user needs emergency help under a certain emergency, he can only trigger the device to send help information by manually clicking a physical button or inputting a command through voice. In the case of sudden illness and inability to act, users are often unable to actively trigger the emergency help function.
而本申请实施例中,通过可穿戴式设备采集人体生理数据,并通过采集的外界音频数据进行分析判断是否满足触发紧急求助功能的条件,当满足条件时,则触发紧急求助功能,避免用户手动触发,在特殊情况下能够实现紧急求助功能的自动触发,提高紧急求助的及时性。However, in the embodiment of the present application, the wearable device collects human physiological data, and analyzes the collected external audio data to determine whether the conditions for triggering the emergency help function are met. Trigger, in special circumstances, the automatic triggering of the emergency help function can be realized, and the timeliness of emergency help can be improved.
本申请实施例提供的紧急求助功能的触发方法包括:The triggering method of the emergency help function provided by the embodiment of the present application includes:
基于可穿戴式设备中传感器采集到的传感器数据确定人体生理数据;Determine human physiological data based on sensor data collected by sensors in the wearable device;
响应于用人体理数据满足第一条件,通过麦克风进行音频采集,得到音频数据;In response to the user's physical data meeting the first condition, audio collection is performed through a microphone to obtain audio data;
响应于音频数据满足第二条件,触发紧急求助功能。In response to the audio data satisfying the second condition, the emergency assistance function is triggered.
可选的,响应于音频数据满足第二条件,触发紧急求助功能,包括:Optionally, in response to the audio data meeting the second condition, triggering an emergency help function, including:
对音频数据进行音频分离,得到人声音频数据和环境声音频数据;Audio separation is performed on the audio data to obtain human voice audio data and ambient sound audio data;
对人声音频数据进行识别,得到人声识别结果;Identify the human voice audio data to obtain the human voice recognition result;
对环境声音频数据进行识别,得到环境声识别结果;Identify the ambient sound audio data to obtain the ambient sound identification result;
响应于人声识别结果和/或环境声识别结果指示音频数据满足第二条件,触发紧急求助功能。The emergency assistance function is triggered in response to the human voice recognition result and/or the ambient sound recognition result indicating that the audio data satisfies the second condition.
可选的,对人声音频数据进行识别,得到人声识别结果,包括:Optionally, identify the human voice audio data to obtain a voice recognition result, including:
对人声音频数据进行情绪识别,得到人声情绪信息;Perform emotion recognition on vocal audio data to obtain vocal emotional information;
对人声音频数据进行音频文本转换,得到人声文本;对人声文本进行关键词匹配,得到关键词匹配结果,关键词匹配结果用于指示人声文本中是否包含预设关键词;Perform audio-to-text conversion on the human voice audio data to obtain human voice text; perform keyword matching on the human voice text to obtain a keyword matching result, and the keyword matching result is used to indicate whether the human voice text contains preset keywords;
将人声情绪信息和/或关键词匹配结果确定为人声识别结果;Determine the human voice emotion information and/or the keyword matching result as the human voice recognition result;
对环境声音频数据进行识别,得到环境声识别结果,包括:Identify ambient sound audio data to obtain ambient sound identification results, including:
对环境声音频数据进行环境识别,得到环境信息,并将环境信息确定为环境声识别结果,环境信息用于表征当前所处环境的环境类型。The environmental sound audio data is subjected to environmental recognition to obtain environmental information, and the environmental information is determined as the environmental sound recognition result, and the environmental information is used to represent the environmental type of the current environment.
可选的,响应于人声识别结果和/或环境声识别结果指示音频数据满足第二条件,触发紧急求助功能,包括:Optionally, in response to the human voice recognition result and/or the ambient sound recognition result indicating that the audio data meets the second condition, triggering an emergency help function, including:
响应于人声情绪信息指示预设情绪,和/或关键词匹配结果指示人声文本中包含预设关键词,和/或环境信息指示处于安静环境,确定音频数据满足第二条件,触发紧急求助功能。In response to the vocal emotion information indicating a preset emotion, and/or the keyword matching result indicating that the vocal text contains a preset keyword, and/or the environmental information indicating a quiet environment, determine that the audio data satisfies the second condition, and trigger emergency help Function.
可选的,响应于环境信息指示处于安静环境,确定音频数据满足第二条件,触发紧急求助功能,包括:Optionally, in response to the environment information indicating that it is in a quiet environment, it is determined that the audio data meets the second condition, and an emergency help function is triggered, including:
响应于环境信息指示处于安静环境,获取当前时间;In response to the environment information indicating that the environment is in a quiet environment, obtain the current time;
响应于当前时间位于预设时段,确定音频数据满足第二条件,并触发紧急求助功能。In response to the current time being within the preset time period, it is determined that the audio data satisfies the second condition, and the emergency help function is triggered.
可选的,响应于人体生理数据满足第一条件,通过麦克风进行音频采集,得到音频数据,包括:Optionally, in response to the human physiological data meeting the first condition, audio collection is performed through a microphone to obtain audio data, including:
基于连续的人体生理数据,确定人体生理数据的波动幅度;Determine the fluctuation range of the human physiological data based on the continuous human physiological data;
响应于波动幅度大于幅度阈值,确定人体生理数据满足第一条件,并通过麦克风进行音频采集,得到音频数据。In response to the fluctuation amplitude being greater than the amplitude threshold, it is determined that the physiological data of the human body satisfies the first condition, and audio data is obtained by collecting audio through the microphone.
可选的,人体生理数据包括心率数据和压力数据中的至少一种;Optionally, the human physiological data includes at least one of heart rate data and stress data;
波动幅度包括心率波动幅度和压力波动幅度中的至少一种。The fluctuation range includes at least one of a heart rate fluctuation range and a pressure fluctuation range.
可选的,基于可穿戴式设备中传感器采集到的传感器数据确定人体生理数据之后,方法还包括:Optionally, after determining human physiological data based on sensor data collected by sensors in the wearable device, the method further includes:
响应于人体生理数据满足第一条件,进行风险提示;In response to the human physiological data meeting the first condition, a risk prompt is performed;
响应于音频数据满足第二条件,触发紧急求助功能,包括:In response to the audio data meeting the second condition, triggering an emergency help function, including:
响应于音频数据满足第二条件,且未接收到对风险提示的正面反馈,触发紧急求助功能,正面反馈用于指示人体生理数据正常。In response to the audio data meeting the second condition, and no positive feedback on the risk prompt is received, an emergency help function is triggered, and the positive feedback is used to indicate that the human physiological data is normal.
可选的,触发紧急求助功能,包括:Optionally, trigger the emergency help function, including:
向预设紧急联系人发送求助信息或发起紧急通讯,求助信息中包含音频数据和地理位置信息。Send a help message or initiate an emergency communication to the preset emergency contact. The help message includes audio data and geographic location information.
请参考图1,其示出了本申请一个示例性实施例提供的实施环境的示意图。该实施环境中包括可穿戴式设备110和移动终端120。Please refer to FIG. 1 , which shows a schematic diagram of an implementation environment provided by an exemplary embodiment of the present application. The implementation environment includes the wearable device 110 and the mobile terminal 120 .
可穿戴式设备110具有采集人体生理数据的功能,其可以是智能手表或智能手环等具有采集人体生理数据功能的设备,本申请实施例并不对可穿戴式设备110的具体设备类型进行限定。The wearable device 110 has the function of collecting human physiological data, which may be a device with the function of collecting human physiological data, such as a smart watch or a smart bracelet. The embodiment of the present application does not limit the specific device type of the wearable device 110 .
在一种可能的实施方式中,可穿戴式设备110具有移动数据通信能力,在不借助其他设备的情况下可以实现数据通信以及通话功能。In a possible implementation manner, the wearable device 110 has a mobile data communication capability, and can implement data communication and call functions without the aid of other devices.
在另一种可能的实施方式中,可穿戴式设备110与移动终端120之间建立有无线通信连接,从而通过该无线通信连接实现数据通信以及通话功能,其中,该无线通信连接可以是蓝牙连接。In another possible implementation manner, a wireless communication connection is established between the wearable device 110 and the mobile terminal 120, so as to realize data communication and call functions through the wireless communication connection, wherein the wireless communication connection may be a Bluetooth connection .
移动终端120是具有移动数据通信能力的电子设备,其可以是智能手机、平板电脑等电子设备,本申请实施例并不对移动终端120的具体设备类型进行限定。The mobile terminal 120 is an electronic device with mobile data communication capability, which may be an electronic device such as a smart phone, a tablet computer, etc. The embodiment of the present application does not limit the specific device type of the mobile terminal 120 .
在一种可能的应用场景下,移动终端120通过对可穿戴式设备110采集到的人体生理数据进行分析,判断是否满足第一条件,当对人体生理数据的判断结果满足第一条件时,通过麦克风组件采集外界音频数据,并对音频数据进行分析,判断音频数据是否满足第二条件,当对音频数据的判断结果满足第二条件时,确定用户当前需要紧急求助,从而主动触发紧急求助功能。In a possible application scenario, the mobile terminal 120 judges whether the first condition is satisfied by analyzing the human physiological data collected by the wearable device 110, and when the judgment result of the human physiological data satisfies the first condition, the The microphone component collects external audio data, analyzes the audio data, and determines whether the audio data satisfies the second condition. When the judgment result of the audio data satisfies the second condition, it is determined that the user currently needs emergency assistance, thereby actively triggering the emergency assistance function.
在另一种可能的应用场景下,人体生理数据的分析、音频数据的采集以及分析步骤均由可穿戴式设备110执行,当确定出满足紧急求助功能的触发条件时,可穿戴式设备110触发自身的紧急求助功能,或者,通过移动终端120触发紧急求助功能。In another possible application scenario, the analysis of human physiological data, the collection of audio data, and the analysis steps are all performed by the wearable device 110. When it is determined that the triggering condition of the emergency help function is satisfied, the wearable device 110 triggers the Its own emergency help function, or trigger the emergency help function through the mobile terminal 120 .
为了方便描述,下述各个实施例以紧急求助功能的触发方法应用于终端为例进行说明。For the convenience of description, the following embodiments are described by taking an example that a method for triggering an emergency help function is applied to a terminal.
图2是本申请实施例提供的紧急求助功能的触发方法的流程图。该方法包 括:FIG. 2 is a flowchart of a method for triggering an emergency help function provided by an embodiment of the present application. The method includes:
步骤201,基于可穿戴式设备中传感器采集到的传感器数据确定人体生理数据。Step 201: Determine human physiological data based on sensor data collected by sensors in the wearable device.
可穿戴式设备通过内置的传感器采集传感器数据,通过对传感器数据进行分析并确定相应的人体生理数据。根据传感器数据得到人体生理数据的过程可通过可穿戴式设备,或绑定的移动终端执行。当可穿戴式设备具有分析传感器数据的功能时,可直接进行人体数据监测;当可穿戴式设备不具备分析传感器数据功能时,通过无线蓝牙或网络等方式将传感器数据发送至绑定的移动终端,由移动终端进行处理,得到各项人体生理数据。The wearable device collects sensor data through built-in sensors, analyzes the sensor data and determines the corresponding human physiological data. The process of obtaining human physiological data according to the sensor data can be performed by a wearable device or a bound mobile terminal. When the wearable device has the function of analyzing sensor data, it can directly monitor human body data; when the wearable device does not have the function of analyzing sensor data, the sensor data can be sent to the bound mobile terminal through wireless Bluetooth or network. , processed by the mobile terminal to obtain various human physiological data.
本实施例以可穿戴式设备基于传感器数据确定人体生理数据为例进行说明。This embodiment is described by taking the wearable device determining human physiological data based on sensor data as an example.
可穿戴式设备通过传感器实时采集人体生理数据,并监测人体生理数据的变化情况。采集的人体生理数据可以是心率数据,压力数据和血氧浓度数据中的至少一种数据,相应的,人体生理数据的变化情况包括心率波动情况,压力波动情况和血氧浓度变化情况中的至少一种。Wearable devices collect human physiological data in real time through sensors, and monitor changes in human physiological data. The collected human physiological data may be at least one of heart rate data, pressure data and blood oxygen concentration data. Correspondingly, changes in the human physiological data include at least one of heart rate fluctuations, pressure fluctuations and blood oxygen concentration changes. A sort of.
其中,心率数据通过可穿戴式设备内置的心率传感器获得,基本工作原理是利用人体组织在血管搏动时所造成的透光率的不同来进行脉搏测量,心率传感器采集数据后,经过光电转换器转换为电信号输出人体心率波形图;在采集的心率数据的基础上,结合压力计算模型对心率数据进行处理可获得压力数据,压力数据可以反应人体当前的压力状态;血氧浓度数据可通过光电传感器检测人体血液获得,基本工作原理是使用特定波长的近红外光作为射入光源,测定通过人体组织的光传导强度,根据测得的光传导的强度值计算血红蛋白浓度及血氧饱和度,对人体血氧浓度进行监测对突发疾病预测具有重要作用。Among them, the heart rate data is obtained through the built-in heart rate sensor of the wearable device. The basic working principle is to use the difference in light transmittance caused by the pulsation of blood vessels in the human body to measure the pulse. After the heart rate sensor collects the data, it is converted by a photoelectric converter. Output the human heart rate waveform for the electrical signal; on the basis of the collected heart rate data, combine with the pressure calculation model to process the heart rate data to obtain the pressure data, which can reflect the current stress state of the human body; the blood oxygen concentration data can be obtained through the photoelectric sensor It is obtained by detecting human blood. The basic working principle is to use near-infrared light of a specific wavelength as the incident light source to measure the light transmission intensity through human tissue, and calculate the hemoglobin concentration and blood oxygen saturation according to the measured light transmission intensity value. The monitoring of blood oxygen concentration plays an important role in the prediction of sudden disease.
步骤202,响应于人体生理数据满足第一条件,通过麦克风进行音频采集,得到音频数据。 Step 202 , in response to the human physiological data satisfying the first condition, audio collection is performed through a microphone to obtain audio data.
当可穿戴式设备监测到人体生理数据满足第一条件,即监测到人体生理数据符合紧急情况下用户的生理特征,包括人体生理数据超过或低于正常生理指标范围,人体生理数据波动幅度超过正常范围,人体生理数据变化异常等,终端通过麦克风采集外界音频数据。只有监测到人体生理数据满足第一条件时,才会触发麦克风进行音频采集,以节省功耗,当监测的人体生理数据不满足第一条件,即各项人体生理数据都正常的情况下,不触发麦克风采集音频数据。When the wearable device detects that the physiological data of the human body meets the first condition, that is, the monitored physiological data of the human body conforms to the physiological characteristics of the user in emergency situations, including that the physiological data of the human body exceeds or falls below the normal physiological index range, and the fluctuation range of the physiological data of the human body exceeds the normal range. range, abnormal changes in human physiological data, etc., the terminal collects external audio data through a microphone. Only when the monitored human physiological data meets the first condition, will the microphone be triggered to perform audio collection to save power consumption. When the monitored human physiological data does not meet the first condition, that is, when all human physiological data Trigger the microphone to collect audio data.
通过麦克风采集外界音频数据可以包括如下情况中的至少一种:Collecting external audio data through a microphone may include at least one of the following situations:
1、可穿戴式设备设置有麦克风组件。当可穿戴式设备监测到人体生理数据符合紧急情况下用户的生理特征时,通过麦克风组件采集外界音频数据,音频数据的时长可以是预设时长或用户调节时长。1. The wearable device is provided with a microphone assembly. When the wearable device detects that the physiological data of the human body conforms to the physiological characteristics of the user in emergency situations, the external audio data is collected through the microphone component, and the duration of the audio data may be a preset duration or a user-adjusted duration.
2、可穿戴式设备不具备麦克风组件,移动终端具备采集音频数据功能。当移动终端监测到人体生理数据符合紧急情况下用户的人体生理特征时,开启麦克风采集音频数据。2. The wearable device does not have a microphone component, and the mobile terminal has the function of collecting audio data. When the mobile terminal detects that the physiological data of the human body conforms to the physiological characteristics of the user's human body in an emergency, the microphone is turned on to collect audio data.
可选的,当可穿戴设备不具备麦克风组件时,可穿戴设备监测到人体生理 数据符合紧急情况下用户的生理特征时,向移动终端发送音频数据采集指令,对应移动终端接收到该音频数据采集指令后,开启麦克风采集音频数据。Optionally, when the wearable device does not have a microphone component, when the wearable device detects that the physiological data of the human body conforms to the physiological characteristics of the user in an emergency, it sends an audio data collection instruction to the mobile terminal, and the corresponding mobile terminal receives the audio data collection. After the command, turn on the microphone to collect audio data.
可选的,可穿戴设备将采集到的人体生理数据发送给移动终端,由移动终端基于人体生理数据进行判断,并在确定人体生理数据符合紧急情况下的人体生理特征时,开启麦克风采集音频数据。Optionally, the wearable device sends the collected human physiological data to the mobile terminal, and the mobile terminal makes a judgment based on the human physiological data, and when it is determined that the human physiological data conforms to the human physiological characteristics in an emergency, the microphone is turned on to collect audio data. .
步骤203,响应于音频数据满足第二条件,触发紧急求助功能。 Step 203, in response to the audio data meeting the second condition, trigger an emergency help function.
通过使用麦克风采集音频数据后,终端对音频数据进行处理和分析,当对音频数据的分析结果满足第二条件时,即对音频数据的处理结果满足紧急情况下的声音特征,确定用户当前需要紧急求助,触发紧急求助功能,触发紧急求助功能的操作由可穿戴式设备执行或移动终端执行。After collecting audio data by using a microphone, the terminal processes and analyzes the audio data. When the analysis result of the audio data satisfies the second condition, that is, the processing result of the audio data satisfies the sound characteristics in emergency situations, it is determined that the user currently needs urgent Ask for help, trigger the emergency help function, and the operation of triggering the emergency help function is performed by the wearable device or the mobile terminal.
可选的,当对音频数据的处理和分析由可穿戴设备执行时,也就是说,可穿戴设备分析得到用户需要紧急求助,则优先由可穿戴设备触发紧急求助功能;同理,若由终端分析得到用户需要紧急求助,则优先由终端触发紧急求助功能,可以提高紧急救助功能触发的及时性。Optionally, when the processing and analysis of the audio data is performed by the wearable device, that is to say, the wearable device analyzes that the user needs emergency help, the wearable device will give priority to triggering the emergency help function; After analyzing that the user needs emergency help, the terminal will give priority to triggering the emergency help function, which can improve the timeliness of triggering the emergency help function.
对采集的音频数据进行处理包括如下情况中的至少一种:Processing the collected audio data includes at least one of the following situations:
1、可穿戴式设备具备音频数据处理和分析能力时,可穿戴式设备直接对采集的音频数据进行处理分析,根据数据处理的结果判断是否满足第二条件。1. When the wearable device has the audio data processing and analysis capabilities, the wearable device directly processes and analyzes the collected audio data, and judges whether the second condition is satisfied according to the result of the data processing.
2、可穿戴式设备不具备音频数据处理分析能力时,可穿戴式设备通过无线蓝牙或网络将采集的音频数据发送至绑定的移动终端,通过移动终端对音频数据进行处理分析,判断音频数据是否满足第二条件。2. When the wearable device does not have the ability to process and analyze audio data, the wearable device sends the collected audio data to the bound mobile terminal through wireless Bluetooth or the network, and processes and analyzes the audio data through the mobile terminal to determine the audio data. whether the second condition is met.
3、可穿戴式设备不具备麦克风组件同时也无法对音频数据进行处理时,由可穿戴式设备绑定的移动终端确定是否满足第一条件和第二条件,当移动终端接收到可穿戴式设备发送的人体生理数据满足第一条件时,通过麦克风组件采集音频数据,并对采集的音频数据进行分析和处理,判断是否满足第二条件。3. When the wearable device does not have a microphone component and cannot process audio data, the mobile terminal bound to the wearable device determines whether the first and second conditions are met. When the mobile terminal receives the wearable device When the sent human physiological data satisfies the first condition, audio data is collected through the microphone assembly, and the collected audio data is analyzed and processed to determine whether the second condition is met.
触发紧急求助功能后,终端通过预设方式向紧急联系人发起紧急求助,发起紧急求助的方式可以包括如下情况中的至少一种:After the emergency help function is triggered, the terminal initiates emergency help to the emergency contact in a preset manner, and the method for initiating emergency help may include at least one of the following situations:
1、可穿戴式设备具备语音通话功能。当音频数据的判断结果满足第二条件时,可穿戴式设备通过内置的语音通话组件拨通紧急联系人发起紧急通讯,向对方寻求帮助,紧急联系人可以为预先设置的家人或朋友,同时也可以将紧急联系人设置为公安报警***或急救中心。1. The wearable device has the function of voice calling. When the judgment result of the audio data satisfies the second condition, the wearable device dials the emergency contact through the built-in voice call component to initiate emergency communication, and seeks help from the other party. The emergency contact can be a preset family member or friend, and also The emergency contact can be set as the public security alarm system or emergency center.
2、可穿戴式设备具备发送信息功能。当音频数据的判断结果满足第二条件时,向紧急联系人发送求助信息,求助信息可以是提前设置好的语音信息或文本信息;在可穿戴式设备在已接入医疗机构的前提下,可直接向定点医疗机构发送求助信息,提供针对性救助。2. The wearable device has the function of sending information. When the judgment result of the audio data satisfies the second condition, send help information to the emergency contact. The help information can be voice information or text information set in advance; on the premise that the wearable device has been connected to a medical institution, it can Send help information directly to designated medical institutions to provide targeted assistance.
3、可穿戴式设备不具备通话功能或语音通话功能。当音频数据的判断结果满足第二条件时,通过可穿戴式设备绑定的移动终端向紧急联系人发送求助信息或发起紧急通讯。3. Wearable devices do not have call function or voice call function. When the judgment result of the audio data satisfies the second condition, send help information or initiate emergency communication to the emergency contact through the mobile terminal bound to the wearable device.
综上所述,本申请实施例提供的紧急求助功能的触发方法,基于可穿戴式设备内的传感器实时监测人体生理数据,当监测到人体生理数据满足第一条件 时,即人体生理数据发生异常,判断用户可能出现紧急状况,从而通过麦克风采集外界音频数据,并对音频数据进行分析,进而在音频数据满足第二条件时,确定用户处于紧急求助状态,并触发紧急求助功能;采用本申请实施例提供的方法,基于人体生理数据和音频数据进行紧急求助状态识别,能够在用户无法手动触发紧急求助功能的情况下实现紧急求助功能的自动触发,提高了紧急求助功能的触发及时性;同时,以人体生理数据和音频数据共同作为触发依据,有助于降低误触发概率,提高触发时机的准确性。To sum up, the method for triggering the emergency help function provided by the embodiment of the present application is based on the real-time monitoring of human physiological data based on the sensors in the wearable device. When the monitored human physiological data meets the first condition, that is, the human physiological data is abnormal. , judging that the user may be in an emergency situation, so as to collect external audio data through the microphone, and analyze the audio data, and then when the audio data meets the second condition, determine that the user is in an emergency state, and trigger the emergency help function; The method provided by the example, based on human physiological data and audio data for emergency help state identification, can realize the automatic triggering of the emergency help function when the user cannot manually trigger the emergency help function, and improve the triggering timeliness of the emergency help function; at the same time, Taking human physiological data and audio data together as triggering basis helps to reduce the probability of false triggering and improve the accuracy of triggering timing.
图3是本申请另一个示例性实施例提供的紧急求助功能的触发方法的流程图,该方法包括:3 is a flowchart of a method for triggering an emergency help function provided by another exemplary embodiment of the present application, and the method includes:
步骤301,基于可穿戴式设备中传感器采集到的传感器数据确定人体生理数据。Step 301: Determine human physiological data based on sensor data collected by sensors in the wearable device.
基于可穿戴式设备内的传感器监测人体生理数据,可穿戴式设备可以是智能手表或手环等具有监测人体生理数据功能的设备,用户通过可穿戴式设备实时监测人体生理数据,具体可参考步骤201,本申请实施例不再详细赘述。Based on the sensor in the wearable device to monitor human physiological data, the wearable device can be a device with the function of monitoring human physiological data, such as a smart watch or a wristband. Users can monitor human physiological data in real time through the wearable device. For details, please refer to the steps 201, the embodiments of the present application will not be described in detail again.
在一种可能的实施方式中,终端确定出的人体生理数据包括心率数据和压力数据中的至少一种。In a possible implementation manner, the human physiological data determined by the terminal includes at least one of heart rate data and stress data.
步骤302,基于连续的人体生理数据,确定人体生理数据的波动幅度。Step 302: Determine the fluctuation range of the human physiological data based on the continuous human physiological data.
正常情况下,用户的人体生理数据变化通常较为平稳,而在需要紧急求助的情况下,用户的人体生理数据变化通常会发生较大幅度的波动(比如心率突然上升),基于人体生理数据的上述特性,本申请实施例中,终端基于连续确定出的人体生理数据,确定人体生理数据的波动幅度,从而基于波动幅度确定人体生理数据是否满足第一条件。Under normal circumstances, the changes of the user's human physiological data are usually relatively stable, but in the case of emergency help, the user's human physiological data usually fluctuates greatly (such as a sudden increase in heart rate). In this embodiment of the present application, the terminal determines the fluctuation range of the human physiological data based on the continuously determined human physiological data, so as to determine whether the human physiological data meets the first condition based on the fluctuation range.
在一种可能的实施方式中,终端获取连续n个时刻的人体生理数据,并计算n个时刻下人体生理数据的数据方差,从而将该数据方差确定为人体生理数据的波动幅度。其中,当人体生理数据为心率数据时,该波动幅度为心率波动幅度,当人体生理数据为压力数据时,该波动幅度为压力波动幅度。当然,终端还可以根据人体生理数据的峰值、标准差等参数确定波动幅度,本申请实施例对此不作限定。In a possible implementation manner, the terminal acquires human physiological data at n consecutive times, and calculates the data variance of the human physiological data at n times, so as to determine the data variance as the fluctuation range of the human physiological data. Wherein, when the human body physiological data is heart rate data, the fluctuation range is the heart rate fluctuation range, and when the human body physiological data is pressure data, the fluctuation range is the pressure fluctuation range. Of course, the terminal may also determine the fluctuation range according to parameters such as the peak value and standard deviation of the human physiological data, which is not limited in this embodiment of the present application.
进一步的,终端检测人体生理数据的波动幅度是否大于幅度阈值,若大于,则确定人体生理数据符合紧急求助状态下的生理特征,并执行步骤303;若小于,则确定人体生理数据不符合紧急求助状态下的生理特征,并继续进行人体生理数据监测。Further, the terminal detects whether the fluctuation range of the human physiological data is greater than the amplitude threshold. If it is greater than the amplitude threshold, it is determined that the human physiological data conforms to the physiological characteristics of the emergency help state, and step 303 is executed; Physiological characteristics of the state, and continue to monitor human physiological data.
可选的,该幅度阈值可以预先设置,或者,基于用户的正常人体生理数据计算得到。可选的,可以根据不同的人体生理数据,设置不同的幅度阈值。Optionally, the amplitude threshold may be preset, or calculated based on the normal human physiological data of the user. Optionally, different amplitude thresholds may be set according to different human physiological data.
步骤303,响应于波动幅度大于幅度阈值,确定人体生理数据满足第一条件,并通过麦克风进行音频采集,得到音频数据。 Step 303 , in response to the fluctuation amplitude being greater than the amplitude threshold, it is determined that the physiological data of the human body meets the first condition, and audio is collected through a microphone to obtain audio data.
当监测到人体生理数据在预设时间内的波动幅度超过幅度阈值时,终端确定人体生理数据满足第一条件,从而触发麦克风采集音频数据。其中,预设时间可以是30s。When it is detected that the fluctuation range of the human physiological data within the preset time exceeds the amplitude threshold, the terminal determines that the human physiological data meets the first condition, thereby triggering the microphone to collect audio data. The preset time may be 30s.
可选的,当监测到至少一种人体生理数据在预设时间内的波动幅度超过其对应的幅度阈值时,终端确定人体生理数据满足第一条件,从而触发麦克风采集音频数据。Optionally, when it is monitored that the fluctuation range of at least one kind of human physiological data exceeds its corresponding amplitude threshold within a preset time, the terminal determines that the human physiological data meets the first condition, thereby triggering the microphone to collect audio data.
可选的,用户可以预先设定重点监测一种或多种人体生理数据,进而在该人体生理数据的波动幅度超过幅度阈值时,终端确定人体生理数据满足第一条件。示意性的,若用户患有“心脏类疾病”,预先设置监测心率数据,则对应的,当确定心率数据的波动幅度超过幅度阈值时,终端确定人体生理数据满足第一条件。Optionally, the user may preset to focus on monitoring one or more kinds of human physiological data, and then when the fluctuation range of the human physiological data exceeds the amplitude threshold, the terminal determines that the human physiological data meets the first condition. Illustratively, if the user suffers from a "heart disease" and the monitoring heart rate data is preset, correspondingly, when it is determined that the fluctuation range of the heart rate data exceeds the amplitude threshold, the terminal determines that the human physiological data meets the first condition.
在一种可能的应用场景下,当可穿戴式设备监测到当前人体生理数据的波动幅度超过幅度阈值,此时移动终端或可穿戴式设备可以发出震动或响铃等方式作为提醒。响应于人体生理数据满足第一条件,可穿戴式设备开启麦克风采集外界音频数据并开始计时,麦克风采集外界音频时长可以为预设时长或用户提前设定时长,当计时时长达到设定时长时,停止通过麦克风采集外界音频数据,采集的音频数据存储于可穿戴式设备内。In a possible application scenario, when the wearable device detects that the fluctuation range of the current human physiological data exceeds the amplitude threshold, the mobile terminal or wearable device can send out vibrations or ringing as a reminder. In response to the human physiological data meeting the first condition, the wearable device turns on the microphone to collect the external audio data and starts timing, and the duration of the microphone to collect the external audio may be a preset duration or a duration set in advance by the user, and when the timing duration reaches the set duration, Stop collecting external audio data through the microphone, and the collected audio data is stored in the wearable device.
在一种可能的实施方式中,可穿戴式设备的存储空间有限,可穿戴式设备可以将采集的历史音频数据通过蓝牙或网络传输至绑定的移动终端。In a possible implementation manner, the wearable device has limited storage space, and the wearable device can transmit the collected historical audio data to the bound mobile terminal through Bluetooth or the network.
可选的,可穿戴设备设备可以定期将历史音频数据删除,以避免存储空间被历史音频数据占据,而导致无法及时进行当前音频数据的采集。Optionally, the wearable device can periodically delete the historical audio data, so as to avoid the storage space being occupied by the historical audio data, which makes it impossible to collect the current audio data in time.
步骤304,对音频数据进行音频分离,得到人声音频数据和环境声音频数据。Step 304: Perform audio separation on the audio data to obtain human voice audio data and ambient sound audio data.
在紧急场景下,通过麦克风采集到的音频数据可能包含有人声、周围嘈杂的环境声和干扰噪声等,每种声音都对应不同的频段且具有不同的特征,其中的干扰噪声是在采集音频过程中产生的,需要进行过滤,而人声和环境声可能包含有能够判断用户当前紧急状态的重要信息,因此还需要将采集的音频数据中的人声音频和环境声音频进行分离,针对环境声和人声分别进行判断。In emergency scenarios, the audio data collected through the microphone may include human voices, noisy ambient sounds, and interference noise. Each sound corresponds to a different frequency band and has different characteristics. It needs to be filtered, and the human voice and ambient sound may contain important information that can judge the user's current emergency state. Therefore, it is also necessary to separate the human voice audio and ambient sound audio in the collected audio data. and human voices are judged separately.
在一种可能的实施方式中,终端通过滤波算法将采集到的音频数据中的干扰噪声滤除,再针对音频数据中的人声和环境声分别使用不同的算法进行分离,得到人声音频数据和环境声音频数据。In a possible implementation manner, the terminal filters out the interference noise in the collected audio data through a filtering algorithm, and then separates the human voice and ambient sound in the audio data using different algorithms to obtain the human voice audio data. and ambient sound audio data.
在一种可能的实施方式中,由于人声与其他环境声或乐器声具有不同的频率特征,因此可以通过将滤除干扰噪声的音频数据转换为声谱图,从而利用卷积神经网络(Convolutional Neural Network,CNN)对声谱图进行识别,识别人声的声谱信息,再将识别所得的新声谱图转化成音频,最后生成纯人声音频数据;进一步的,终端基于音频数据和人声音频数据,分离得到环境声音频数据。本申请实施例并不对音频分离所采用的具体方式进行限定。In a possible implementation, since the human voice has different frequency characteristics from other ambient sounds or musical instrument sounds, the convolutional neural network (Convolutional Neural Network) can be used to convert the audio data filtered out of the interference noise into a spectrogram. Neural Network, CNN) recognizes the spectrogram, recognizes the spectrogram information of the human voice, and then converts the new spectrogram obtained from the recognition into audio, and finally generates pure human voice audio data; further, the terminal is based on the audio data and human voice. The sound and audio data are separated to obtain ambient sound audio data. The embodiments of the present application do not limit the specific manner used for audio separation.
步骤305,对人声音频数据进行识别,得到人声识别结果。Step 305: Identify the human voice audio data to obtain a human voice recognition result.
为了提高用户在遇到紧急状态下触发紧急求助的准确性,需要对获取到的人声音频数据进行识别,确定人声识别结果,人声识别结果在一定程度上可以反应用户的处境是否存在危险。In order to improve the accuracy of triggering emergency help when users encounter an emergency, it is necessary to identify the acquired voice audio data and determine the voice recognition result. The voice recognition result can reflect whether the user's situation is in danger to a certain extent. .
可选的,终端通过人声增强技术将分离得到的人声音频放大处理,便于对音频信息做进一步处理,人声音频数据识别可以通过将处理得到的人声音频与 提前录制的用户音频进行对比,确认采集得到的音频数据中的人声是否为用户本人的声音,以此来判断用户状态;或,通过对人声音频进行人声文本转化,根据文本信息内容作出判断。如图4所示,步骤305可以包括以下步骤。Optionally, the terminal amplifies and processes the separated vocal audio through the vocal enhancement technology, so as to facilitate further processing of the audio information, and the vocal audio data can be identified by comparing the processed vocal audio with the pre-recorded user audio. , confirming whether the human voice in the collected audio data is the user's own voice, so as to judge the user's state; or, by transforming the human voice audio into human voice text, making a judgment based on the content of the text information. As shown in FIG. 4, step 305 may include the following steps.
步骤305A,对人声音频数据进行情绪识别,得到人声情绪信息。 Step 305A: Perform emotion recognition on the vocal audio data to obtain vocal emotion information.
终端通过对人声音频数据进行处理和分析,识别用户当前的情绪状态,得到人声情绪信息,人声情绪信息在一定程度上可以反映用户在紧急状态下的真实情绪。The terminal processes and analyzes the vocal audio data, identifies the current emotional state of the user, and obtains vocal emotional information. The vocal emotional information can reflect the user's true emotions in an emergency state to a certain extent.
在一种可能的实施方式中,可以采用基于深度学习的语音情绪识别算法(Speech Emotion Recognition,SER)来识别出人声音频中表达的“愤怒”、“开心”、“恐惧”和“悲伤”等情绪,每种情绪对应用户的情绪状态。当识别出的人声情绪为“开心”时,对应用户可能因为遇到开心的事情导致人体生理数据波动较大,并不需要求助;当识别出的人声情绪为“恐惧”时,用户可能受到人身威胁或突发疾病,此时需要进行紧急求助。但在一些特定场景下,如看恐怖电影时,同样会导致人体生理数据和情绪发生变化,因此,单纯依靠识别人声情绪无法作出准确判断。In a possible implementation, a speech emotion recognition algorithm (Speech Emotion Recognition, SER) based on deep learning can be used to identify "anger", "happy", "fear" and "sadness" expressed in human voice audio Emotions, each corresponding to the user's emotional state. When the identified vocal emotion is "happy", the corresponding user may experience a happy event, which may lead to large fluctuations in human physiological data, and no help is needed; when the identified vocal emotion is "fear", the user may In the event of a personal threat or sudden illness, emergency assistance is required. However, in some specific scenarios, such as watching horror movies, it will also lead to changes in human physiological data and emotions. Therefore, it is impossible to make accurate judgments simply by recognizing human voice emotions.
步骤305B,对人声音频数据进行音频文本转换,得到人声文本;对人声文本进行关键词匹配,得到关键词匹配结果,关键词匹配结果用于指示人声文本中是否包含预设关键词。Step 305B, performing audio-text conversion on the human voice audio data to obtain human voice text; performing keyword matching on the human voice text to obtain a keyword matching result, and the keyword matching result is used to indicate whether the human voice text contains preset keywords .
除了以人声情绪作为一个判断维度外,为了提高人声识别的准确性,终端还可以对人声音频数据进行音频文本转换,得到人声文本,从而根据人声文本中是否包含与紧急求助相关的关键词,判断用户当前是否处于紧急求助状态。In addition to taking the emotion of the human voice as a judgment dimension, in order to improve the accuracy of human voice recognition, the terminal can also perform audio-text conversion on the human voice audio data to obtain the human voice text, so as to determine whether the voice text contains information related to emergency help. keyword to determine whether the user is currently in an emergency state.
在一种可能的实施方式中,在获取的人声音频数据的基础上进行音频文本转换,通过使用声学模型和语言模型提取人声音频数据中的声学特征,进一步通过算法将人声音频转化为人声文本,如使用自动语音识别技术(Automatic Speech Recognition,ASR)将实时输入的语音信号转化为文本输出。In a possible implementation, audio-to-text conversion is performed on the basis of the acquired human voice audio data, and the acoustic features in the human voice audio data are extracted by using an acoustic model and a language model, and the human voice audio is further converted into human voice audio through an algorithm. Acoustic text, such as using automatic speech recognition technology (Automatic Speech Recognition, ASR) to convert real-time input speech signal into text output.
进一步地,终端需要对人声文本进行识别,对人声文本进行识别在一定程度上可以辅助判断用户的情绪状态,在一些实施例中可以通过对关键词匹配的方式进行判断,通过将转换的人声文本与预设关键词进行匹配,确定人声文本中是否含有预设关键词,预设关键词可以是与紧急求助相关的词语或用户设定的暗语,只要识别出暗语,即代表用户受到人身威胁,立刻触发紧急求助功能。当人声文本匹配过程中匹配到一个或多个预设关键词时,确定用户当前可能受到人身威胁。Further, the terminal needs to recognize the human voice text, and the recognition of the human voice text can assist in judging the emotional state of the user to a certain extent. Match the vocal text with preset keywords to determine whether the vocal text contains preset keywords. The preset keywords can be words related to emergency help or code words set by the user. As long as the code words are recognized, it represents the user Threatened by a person, the emergency help function is triggered immediately. When one or more preset keywords are matched during the human-voice-text matching process, it is determined that the user may currently be threatened personally.
步骤305C,将人声情绪信息和/或关键词匹配结果确定为人声识别结果。 Step 305C, determining the human voice emotion information and/or the keyword matching result as the human voice recognition result.
终端将识别的人声情绪信息和关键词匹配结果中的至少一种确定为人声识别结果。The terminal determines at least one of the recognized human voice emotion information and the keyword matching result as the human voice recognition result.
由于实际应用场景的情况更为复杂多样,因此并非所有场景下均能够识别出人声情绪和关键词,在一种可能的实施方式中,若仅识别出人声情绪信息和关键词匹配结果中的一项,服务器将识别出的一项确定为人声识别结果;若同时识别出人声情绪信息和关键词匹配结果,服务器则将两者均确定为人声识别 结果。Since the actual application scenarios are more complex and diverse, not all scenarios can identify human voice emotions and keywords. In a possible implementation, if only human voice emotion information and keyword matching results are identified , the server determines the recognized item as the human voice recognition result; if both the human voice emotion information and the keyword matching result are recognized at the same time, the server determines both as the human voice recognition result.
可选的,将人声情绪信息或关键词匹配结果中的任意一种确定人声识别结果的准确性较低,为了进一步提高人声识别的准确性,可以将人声情绪信息和关键词匹配结果共同确定为人声识别结果,并对识别的关键词和人声情绪信息进行匹配,通过人声情绪信息和关键词的对应关系确定人声识别结果;若识别的关键词和人声情绪信息是对应关系,确定人声识别结果指示用户当前处于危险状态或安全状态。Optionally, any one of the vocal emotion information or the keyword matching result determines that the accuracy of the vocal recognition result is low. In order to further improve the accuracy of the vocal recognition, the vocal emotion information and the keyword can be matched. The results are jointly determined as the human voice recognition result, and the recognized keywords and the vocal emotion information are matched, and the human voice recognition result is determined by the corresponding relationship between the vocal emotion information and the keywords; if the recognized keywords and the vocal emotion information are Corresponding relationship, it is determined that the human voice recognition result indicates that the user is currently in a dangerous state or a safe state.
在一种可能的实施方式中,为了能够提高判断的准确性,预设关键词可以设置成与人声情绪信息对应的关系。当人声情绪为“开心”时,对应预设关键词可设置为“好开心”,“心情好”或“太好了”等词语,表明用户可能因开心的事情过于兴奋导致人体生理数据的波动幅度超过阈值,并未受到人身威胁;当人声情绪为“恐惧”时,对应预设关键词可设置为“闭嘴”,“杀了你”,“救命”等词语,表明用户处于危险状态。In a possible implementation manner, in order to improve the accuracy of the judgment, the preset keywords may be set in a relationship corresponding to the emotional information of the human voice. When the emotion of the human voice is "happy", the corresponding preset keywords can be set to words such as "very happy", "in a good mood" or "very good", indicating that the user may be too excited by happy things, which may lead to the change of human physiological data. The fluctuation range exceeds the threshold, and there is no personal threat; when the voice emotion is "fear", the corresponding preset keywords can be set to "shut up", "kill you", "help" and other words, indicating that the user is in danger state.
步骤306,对环境声音频数据进行识别,得到环境声识别结果。Step 306: Identify the ambient sound audio data to obtain an ambient sound identification result.
通过人声识别结果判断紧急求助状态在一些特定场合可能会有误判的情况发生,如观看恐怖电影时可能会匹配到预设关键词,但用户并未受到人身威胁,单纯基于人声识别结果并不能作出准确预判,此时还需要对环境声音频数据进行识别,确定周围的环境信息。如图4所示,本步骤可以包括步骤306A。Judging the state of emergency assistance based on the results of human voice recognition may lead to misjudgments in some specific situations. For example, when watching a horror movie, preset keywords may be matched, but the user is not personally threatened. It is purely based on the results of voice recognition. It is not possible to make an accurate prediction. At this time, it is also necessary to identify the ambient sound and audio data to determine the surrounding environment information. As shown in FIG. 4 , this step may include step 306A.
步骤306A,对环境声音频数据进行环境识别,得到环境信息,并将环境信息确定为环境声识别结果,环境信息用于表征当前所处环境的环境类型。 Step 306A: Perform environmental recognition on the audio data of the environmental sound to obtain environmental information, and determine the environmental information as the environmental sound recognition result, where the environmental information is used to represent the environmental type of the current environment.
在一种可能的实施方式中,可以通过将采集的环境声音频与预设的环境音频进行匹配,得到环境声识别结果。其中,预设的环境音频可以为吵闹环境或寂静环境下采集到的音频,还可以是一些特定环境下采集到的音频,如影院环境或运动场环境等,根据匹配内容确定当前环境信息,当匹配的结果为影院环境或吵闹的环境时,指示用户当前正在看电影或在热闹的环境中,无需进行紧急求助,当匹配的结果为寂静环境时,表明用户当前需要进行紧急求助。In a possible implementation manner, the ambient sound recognition result may be obtained by matching the collected ambient sound audio with the preset ambient audio. The preset ambient audio may be audio collected in a noisy environment or a quiet environment, or may be audio collected in some specific environments, such as a theater environment or a sports field environment, etc. The current environment information is determined according to the matching content. When the result of matching is a cinema environment or a noisy environment, it indicates that the user is currently watching a movie or in a lively environment, and there is no need for emergency help. When the matching result is a silent environment, it indicates that the user currently needs emergency help.
在另一种可能的实施方式中,终端对获取的环境声音频数据做分贝值检测,通过分贝值的高低确定用户当前环境是否嘈杂或安静,当分贝值高于阈值时,环境识别结果判定为用户处于嘈杂环境,当分贝值低于阈值时,环境识别结果判定为用户处于安静环境。In another possible implementation, the terminal performs decibel value detection on the acquired ambient sound and audio data, and determines whether the user's current environment is noisy or quiet according to the level of the decibel value. When the decibel value is higher than the threshold, the environment recognition result is determined as The user is in a noisy environment, and when the decibel value is lower than the threshold, the environment recognition result determines that the user is in a quiet environment.
步骤307,响应于人声识别结果和/或环境声识别结果指示音频数据满足第二条件,触发紧急求助功能。Step 307 , in response to the human voice recognition result and/or the ambient sound recognition result indicating that the audio data satisfies the second condition, trigger an emergency help function.
终端以人声识别结果和环境声识别结果中的至少一种作为判断依据,确定音频数据是否满足第二条件,并在音频数据满足第二条件时,触发紧急求助功能。The terminal determines whether the audio data satisfies the second condition based on at least one of the human voice recognition result and the environmental sound recognition result, and triggers an emergency help function when the audio data satisfies the second condition.
在一种可能的实施方式中,当人声识别结果中包含人声情绪信息和关键词匹配结果中的至少一种,且环境声识别结果中包含环境信息时,如图4所示,本步骤可以包括步骤307A。In a possible implementation, when the human voice recognition result contains at least one of human voice emotion information and keyword matching results, and the environmental sound recognition result contains environmental information, as shown in FIG. 4 , this step Step 307A may be included.
步骤307A,当人声情绪信息指示预设情绪,和/或关键词匹配结果指示人声 文本中包含预设关键词,和/或环境信息指示处于安静环境时,确定音频数据满足第二条件,触发紧急求助功能。 Step 307A, when the vocal emotion information indicates a preset emotion, and/or the keyword matching result indicates that the vocal text contains a preset keyword, and/or the environmental information indicates that it is in a quiet environment, it is determined that the audio data satisfies the second condition, Trigger the emergency help function.
终端将识别出的人声情绪信息、关键词匹配结果和环境信息中的至少一种作为判断是否触发紧急求助功能的判断依据,当判断结果满足第二条件时,触发紧急求助功能,当判断结果不满足第二条件时,不触发紧急求助功能。The terminal uses at least one of the identified human voice emotional information, keyword matching results and environmental information as the judgment basis for judging whether to trigger the emergency help function. When the judgment result meets the second condition, the emergency help function is triggered. When the judgment result When the second condition is not met, the emergency help function is not triggered.
在一种可能的实施方式中,可以将人声情绪信息、关键词匹配结果和环境信息中的任意一种,任意两种或三种作为判断依据。通常情况下,以任意一种作为判断依据触发紧急求助功能的概率最大,但同时误触发的可能性也最大,当判断依据增多时,触发紧急求助功能的概率也相应变小,且误触发的可能性也变小,当以三种共同作为判断依据时,其触发紧急求助功能的概率最小,但误触发的可能性最低。下面分别以任意一种、任意两种和三种作为判断依据进行说明。In a possible implementation, any one, any two or three of the human voice emotion information, the keyword matching result and the environmental information may be used as the judgment basis. Under normal circumstances, the probability of triggering the emergency help function with any one of them as the judgment basis is the highest, but at the same time, the possibility of false triggering is also the greatest. The possibility also becomes smaller. When the three common types are used as the judgment basis, the probability of triggering the emergency help function is the smallest, but the possibility of false triggering is the lowest. The following descriptions are given by taking any one, any two, and three as the judgment basis.
在一种可能的实施方式中,以人声情绪信息作为判断依据,当识别的人声情绪信息为预设的“恐惧”情绪时,确定用户当前可能受到人身威胁导致情绪发生改变,进而触发紧急求助功能,当识别出的人声情绪信息为预设的“开心”情绪或未指示预设情绪时,不满足第二条件,即不触发紧急求助功能。In a possible implementation, the emotional information of the human voice is used as the judgment basis, and when the recognized emotional emotional information of the human voice is the preset "fear" emotion, it is determined that the user may currently be threatened by a person causing a change in the emotion, thereby triggering an emergency For the help function, when the identified voice emotion information is a preset "happy" emotion or does not indicate a preset emotion, the second condition is not satisfied, that is, the emergency help function is not triggered.
可选地,以关键词匹配结果作为判断依据来判断是否需要触发紧急求助功能时,当关键词匹配结果指示包含预设关键词时,表明用户处于紧急状态,进而触发紧急求助功能,当关键词匹配结果指示不包含预设关键词时,确定用户并未遇到危险,不触发紧急求助功能。Optionally, when judging whether the emergency help function needs to be triggered based on the keyword matching result, when the keyword matching result indicates that the preset keyword is included, it indicates that the user is in an emergency state, and then the emergency help function is triggered. When the matching result indicates that the preset keyword is not included, it is determined that the user is not in danger, and the emergency help function is not triggered.
可选的,以环境信息作为判断依据来判断是否需要触发紧急求助功能时,当识别出的环境信息为吵闹的环境或分贝值超出设定阈值时,指示用户并未处于紧急状态,当识别的环境信息为寂静的环境或分贝值低于设定阈值时,表明用户处于紧急状态,即触发紧急求助功能。Optionally, when judging whether the emergency help function needs to be triggered based on environmental information, when the identified environmental information is a noisy environment or the decibel value exceeds the set threshold, it indicates that the user is not in an emergency state, and when the identified environment information is a noisy environment or the decibel value exceeds the set threshold When the environmental information is a silent environment or the decibel value is lower than the set threshold, it indicates that the user is in an emergency state, that is, the emergency help function is triggered.
可选的,以人声情绪信息和关键词匹配结果作为判断依据时,当人声情绪信息指示预设情绪,且关键词匹配结果中包含预设关键词时,表明用户当前处于紧急状态,满足第二条件,触发紧急求助功能。Optionally, when the vocal emotion information and the keyword matching result are used as the judgment basis, when the vocal emotion information indicates a preset emotion, and the keyword matching result contains a preset keyword, it indicates that the user is currently in an emergency state, and the satisfaction is satisfied. The second condition is to trigger the emergency help function.
由上述内容可知,以人声情绪信息、关键词匹配结果和环境信息中的任意一种或两种都可以作为判断是否触发紧急求助功能的判断依据,但在一些特殊情况下可能会有误判的情况发生,比如,用户在安静的环境下跑步或做其他剧烈运动时,仅以环境信息进行判断就可能会造成误判。It can be seen from the above content that any one or both of the emotional information of the human voice, the keyword matching results and the environmental information can be used as the basis for judging whether to trigger the emergency help function, but there may be misjudgments in some special cases. For example, when a user runs in a quiet environment or does other strenuous exercise, only making judgments based on environmental information may cause misjudgments.
通过人声情绪信息和关键词匹配结果作为判断依据在一些特殊情况下也可能会出现误判,如看恐怖电影时,由于紧张的气氛和播放的声音会导致用户人体生理数据短暂异常,且可能会匹配到预设关键词,进而误触发紧急求助功能,实际用户并不需要触发紧急求助功能,因此,依靠人声情绪信息和关键词匹配结果同样无法作出准确判断。Using vocal emotion information and keyword matching results as the judgment basis may also cause misjudgment in some special cases, such as watching a horror movie, due to the tense atmosphere and playing sounds, the user's human physiological data will be temporarily abnormal, and may The preset keywords will be matched, and the emergency help function will be triggered by mistake. The actual user does not need to trigger the emergency help function. Therefore, it is also impossible to make an accurate judgment by relying on the emotional information of the human voice and the keyword matching results.
在一种可能的实施方式中,为了进一步提高判断的准确性,降低误触发的概率,还可以在人声识别结果的基础上,结合环境信息作出判断依据,当识别出的人声情绪为预设情绪,且关键词匹配结果指示包含预设关键词,同时环境 声识别结果指示为寂静环境时,确定采集的音频数据满足第二条件,即确定用户处于紧急求助状态,从而自动触发紧急求助功能寻求帮助。In a possible implementation, in order to further improve the accuracy of judgment and reduce the probability of false triggering, a judgment basis can also be made on the basis of the human voice recognition result combined with environmental information. Set the mood, and the keyword matching result indicates that the preset keyword is included, and when the ambient sound recognition result indicates a silent environment, it is determined that the collected audio data satisfies the second condition, that is, it is determined that the user is in an emergency help state, thereby automatically triggering the emergency help function. Get help.
触发紧急求助功能的几种方式参考步骤203,本实施例以具备通话功能、发送信息功能和定位功能的可穿戴式设备为例进行说明。Refer to step 203 for several ways of triggering the emergency help function. In this embodiment, a wearable device having a call function, a message sending function, and a positioning function is used as an example for description.
当可穿戴式设备确定音频数据满足第二条件时,确定用户处于紧急求助状态,触发可穿戴式设备至少给一个紧急联系人发送求助信息或发起紧急通讯,求助信息包含有采集到的音频数据和当前地理位置信息,求助信息的内容可以是预设的文字信息或语音信息,当紧急联系人接收到求助信息后,根据求助信息内容提供针对性帮助。When the wearable device determines that the audio data meets the second condition, it determines that the user is in an emergency state, and triggers the wearable device to send at least one emergency contact a help message or initiate an emergency communication, where the help message includes the collected audio data and The current geographic location information and the content of the help information may be preset text information or voice information. When the emergency contact receives the help information, targeted help is provided according to the content of the help information.
在一些应用场景下,发送紧急求助信息后可能不能第一时间得到救助,触发紧急求助还可以设置为发送紧急求助信息后再发起紧急通讯,紧急联系人可以为预先设置的家人或朋友,同时也可以将紧急联系人设置为公安报警***或急救中心。In some application scenarios, you may not be able to get help immediately after sending the emergency help information. When triggering emergency help, you can also set it to send emergency help information and then initiate emergency communication. The emergency contact can be a preset family member or friend. The emergency contact can be set as the public security alarm system or emergency center.
可选的,可以结合前期的人声识别结果和人体生理数据,确定紧急求助功能的方式,示意性的,若基于人声识别结果和人体生理数据确定用户受到人身威胁,则优先向公安报警***发起求助;若基于人声识别结果确定用户突发疾病,则优先向急救中心发起求助。Optionally, the method of the emergency help function can be determined by combining the previous human voice recognition results and human physiological data. Illustratively, if it is determined based on the human voice recognition results and human physiological data that the user is threatened, the public security alarm system will be given priority. Initiate help; if it is determined that the user has a sudden illness based on the results of human voice recognition, the emergency center will be prioritized for help.
在一种可能的应用场景下,用户可能因深夜突发疾病进入昏迷状态,通过麦克风采集到的音频数据可能检测不到人声情绪信息和关键词,若用户得不到及时的救助可能会出现生命危险。In a possible application scenario, the user may fall into a coma due to a sudden illness in the middle of the night, and the audio data collected through the microphone may not be able to detect human voice emotional information and keywords. Danger to life.
为了尽可能的提高触发紧急求助功能的及时性,同时降低误触发的概率,当环境信息指示处于安静环境时,还可以通过获取当前时间信息作进一步判断。可选的,响应于环境信息指示处于安静环境,获取当前时间,若当前时间位于预设时段,则触发紧急求助功能。In order to improve the timeliness of triggering the emergency help function as much as possible, and at the same time reduce the probability of false triggering, when the environmental information indicates that it is in a quiet environment, further judgment can be made by obtaining the current time information. Optionally, in response to the environment information indicating that the device is in a quiet environment, the current time is obtained, and if the current time is within a preset time period, an emergency help function is triggered.
在一种可能的实施方式中,响应于人声音频数据中检测不到有效的人声情绪信息且人声文本信息匹配不到预设关键词,且通过环境声音频数据识别出当前用户处于安静环境,表明用户当前可能因突发疾病或其他原因无法发出声音,因此还需要结合时间信息作进一步判断。In a possible implementation, in response to the fact that no valid vocal emotion information is detected in the vocal audio data and no preset keywords are matched with the vocal text information, and it is identified through the ambient sound audio data that the current user is quiet environment, indicating that the user may currently be unable to make a sound due to sudden illness or other reasons, so further judgment needs to be combined with time information.
可选的,终端检测获取到的当前时间是否属于预设时段,若属于预设时段,确定处于紧急求助状态,并触发紧急求助功能;若不属于预设时段,确定并非处于紧急求助状态,并继续进行监测。其中,该预设时段可以基于用户的疾病情况自动设定,比如,当用户患有心血管疾病时,该预设时段可以为心血管疾病的多发时段,比如凌晨时段和清晨时段;或者,该预设时段也可以由用户自行设置,本实施例对此不作限定。Optionally, the terminal detects whether the acquired current time belongs to the preset time period, and if it belongs to the preset time period, it determines that it is in an emergency help state, and triggers the emergency help function; if it does not belong to the preset time period, it determines that it is not in the emergency help state, and Continue to monitor. Wherein, the preset time period may be automatically set based on the user's disease condition, for example, when the user suffers from cardiovascular disease, the preset time period may be a frequent period of cardiovascular disease, such as the early morning time period and the early morning time period; The set time period may also be set by the user, which is not limited in this embodiment.
本实施例中,通过使用可穿戴式设备内置的传感器实时监测人体生理数据,当人体生理数据的波动幅度超过幅度阈值,判断用户可能处于危险状态,从而通过麦克风采集外界音频数据作进一步判断,避免长时间进行音频数据采集和分析造成终端功耗增加。In this embodiment, by using the built-in sensor of the wearable device to monitor the human physiological data in real time, when the fluctuation range of the human physiological data exceeds the amplitude threshold, it is judged that the user may be in a dangerous state, so that the external audio data is collected through the microphone for further judgment to avoid Long-term audio data collection and analysis results in increased terminal power consumption.
同时,通过对采集的音频数据中的人声音频数据和环境声音频数据分别处 理和分析,从人声音频数据和环境声音频数据中提取对应的人声特征信息和环境声特征信息,从而根据人声特征信息和环境声特征信息确定用户是否处于紧急求助状态,有助于提高后续紧急求助功能触发时机的准确性。At the same time, by separately processing and analyzing the human voice audio data and the ambient sound audio data in the collected audio data, the corresponding human voice feature information and ambient sound feature information are extracted from the human voice audio data and the ambient sound audio data. The human voice feature information and the ambient sound feature information determine whether the user is in an emergency help state, which helps to improve the accuracy of the trigger timing of the subsequent emergency help function.
此外,通过将获取的人声音频数据中的人声音频转换为人声文本,根据人声文本匹配预设关键词并结合识别出的人声情绪信息,同时将识别的环境信息作为判断用户是否处于危险状态的条件,提高了判断用户处于紧急求助状态的准确性。In addition, by converting the vocal audio in the acquired vocal audio data into vocal text, matching preset keywords according to the vocal text and combining the identified vocal emotional information, and using the identified environmental information as the judgment of whether the user is in a The condition of the dangerous state improves the accuracy of judging that the user is in an emergency state.
为了进一步降低紧急求助功能的误触发概率,在一种可能的实施方式中,在识别出人体生理数据异常时,终端可以在进行音频数据采集和分析的同时进行提示。当用户处于紧急求助状态时,往往无法对提示做出正面反馈,因此当音频数据满足第二条件,且未接收到对提示的正面反馈时,终端确定用户处于紧急求助状态,并主动触发紧急求助功能。反之,若接收到对提示的正面反馈,则确定用户未处于紧急求助状态。下面采用示例性的实施例进行说明。In order to further reduce the probability of false triggering of the emergency help function, in a possible implementation, when an abnormality of human physiological data is identified, the terminal may give a prompt while collecting and analyzing audio data. When the user is in an emergency state, it is often impossible to give positive feedback to the prompt. Therefore, when the audio data meets the second condition and no positive feedback is received for the prompt, the terminal determines that the user is in an emergency state and actively triggers emergency assistance. Function. Conversely, if positive feedback to the prompt is received, it is determined that the user is not in an emergency state. Exemplary embodiments are used for description below.
图5是本申请另一个示例性实施例提供的紧急求助功能的触发方法的流程图,该方法包括:FIG. 5 is a flowchart of a method for triggering an emergency help function provided by another exemplary embodiment of the present application, and the method includes:
步骤501,基于可穿戴式设备中传感器采集到的传感器数据确定人体生理数据。Step 501: Determine human physiological data based on sensor data collected by sensors in the wearable device.
本步骤的实施方式可以参考步骤201,本实施例在此不再赘述。For the implementation of this step, reference may be made to step 201, and details are not described herein again in this embodiment.
步骤502,响应于人体生理数据满足第一条件,通过麦克风采集音频数据并进行风险提示。 Step 502 , in response to the human physiological data meeting the first condition, collect audio data through a microphone and perform a risk prompt.
可选的,当监测的人体生理数据的波动幅度大于幅度阈值时,终端通过麦克风采集音频数据,同时发出风险提示,并接收用户的反馈。Optionally, when the fluctuation range of the monitored human physiological data is greater than the range threshold, the terminal collects audio data through a microphone, issues a risk prompt at the same time, and receives feedback from the user.
其中,用户的反馈包括正面反馈和负面反馈,其中,正面反馈指示非紧急求助状态下引起的人体生理数据异常(不存在风险);负面反馈指示紧急求助状态下引起的人体生理数据异常(存在风险)。Among them, the user's feedback includes positive feedback and negative feedback, wherein, positive feedback indicates abnormal human physiological data caused by non-emergency help (no risk); negative feedback indicates abnormal human physiological data caused by emergency help (risk exists) ).
在一些实施例中,当可穿式戴设备监测到人体心率或压力值在短时间内波动幅度大于幅度阈值时,通过发出震动或声音提示人体生理数据存在异常。相应的,用户可以通过点击物理按键进行正面反馈。In some embodiments, when the wearable device detects that the human heart rate or the pressure value fluctuates more than the amplitude threshold in a short period of time, the wearable device will alert the human body that there is an abnormality in the human physiological data by emitting vibration or sound. Correspondingly, the user can give positive feedback by clicking the physical button.
可选地,风险提示还可以是亮屏提醒,在可穿式戴设备的界面显示提醒信息。如图6所示,当可穿戴式设备610监测用户的人体生理数据发生异常时,通过界面显示信息提示框611提醒用户作出反馈,信息提示框611内包括用户当前出现异常的人体生理数据612,用户通过手动点击的方式确定是否为误判提醒。信息提示框611的显示时长为预设时长,当用户在预设时长内作出正面反馈(比如点击正常按键)时,指示当前用户身体状态良好,停止采集音频数据;可穿戴式设备610在预设时长内接收到负面反馈(比如点击报警按键)或未接收到反馈(比如在信息提示框的显示时长内未接收到对任何按键的点击操作)时,指示用户当前处于紧急求助状态。Optionally, the risk prompt may also be a screen-on prompt, and prompt information is displayed on the interface of the wearable device. As shown in FIG. 6 , when the wearable device 610 monitors the abnormal human physiological data of the user, an information prompt box 611 is displayed on the interface to remind the user to give feedback. The information prompt box 611 includes the abnormal human physiological data 612 of the user currently. The user determines whether it is a misjudgment reminder by manually clicking. The display duration of the information prompt box 611 is a preset duration. When the user makes positive feedback (such as clicking the normal button) within the preset duration, it indicates that the current user is in good physical condition and stops collecting audio data; the wearable device 610 is in the preset duration. When negative feedback is received (such as clicking the alarm button) or no feedback is received (such as no click operation on any button is received within the display time of the information prompt box), it indicates that the user is currently in an emergency state.
可选的,当接收到对风险提示的负面反馈时,可穿戴式设备610直接触发紧急求助功能。当未接收到对风险提示的反馈时,可穿戴式设备610基于音频 数据的识别结果,确定是否需要触发紧急求助功能。Optionally, when negative feedback on the risk prompt is received, the wearable device 610 directly triggers the emergency help function. When no feedback on the risk prompt is received, the wearable device 610 determines whether the emergency help function needs to be triggered based on the recognition result of the audio data.
步骤503,响应于音频数据满足第二条件,且未接收到对风险提示的正面反馈,触发紧急求助功能,正面反馈用于指示人体生理数据正常。 Step 503 , in response to the audio data meeting the second condition and no positive feedback on the risk prompt being received, an emergency help function is triggered, and the positive feedback is used to indicate that the human physiological data is normal.
在一种可能的实施方式中,当音频数据满足第二条件,且在预设时长内未接收到对风险提示的正面反馈(接收到负面反馈或者未接收到反馈)时,终端确定用户处于紧急求助状态,从而触发紧急求助功能。In a possible implementation manner, when the audio data satisfies the second condition and no positive feedback (negative feedback or no feedback) is received for the risk prompt within a preset time period, the terminal determines that the user is in an emergency Help state, thus triggering the emergency help function.
其中,预设时长可以由用户设置,或采用默认设置,预设时长可以是15s。The preset duration may be set by the user, or the default setting may be adopted, and the preset duration may be 15s.
示意性的,如图6所示,可穿戴式设备610显示信息提示框611后,若在20s内未接收到对“正常”按键或“报警”按键的点击操作,可穿戴式设备610即向移动终端620发送触发指令,移动终端620接收到触发指令后,即触发紧急求助功能(向紧急联系人儿子发送预设短信)。Illustratively, as shown in FIG. 6 , after the wearable device 610 displays the information prompt box 611, if the click operation on the “normal” button or the “alarm” button is not received within 20s, the wearable device 610 will send an The mobile terminal 620 sends the trigger instruction, and after receiving the trigger instruction, the mobile terminal 620 triggers the emergency help function (sends a preset short message to the emergency contact son).
本实施例中,当监测人体生理数据异常时,终端进行风险提示,提醒用户作出相应反馈;若接收到用户作出的正面反馈,指示不需要触发紧急求助功能;若接收到负面反馈或没有接收到反馈,则通过对采集的音频数据进行分析,进一步确定是否满足紧急求助功能的触发条件,降低紧急求助功能的误触发概率。In this embodiment, when the monitored physiological data of the human body is abnormal, the terminal performs a risk prompt to remind the user to give corresponding feedback; if it receives positive feedback from the user, it indicates that the emergency help function does not need to be triggered; if it receives negative feedback or does not receive Feedback, then by analyzing the collected audio data, it is further determined whether the triggering conditions of the emergency help function are met, and the probability of false triggering of the emergency help function is reduced.
图7是本申请一个示例性实施例提供的紧急求助功能的触发装置的结构框图,该装置包括:7 is a structural block diagram of an apparatus for triggering an emergency help function provided by an exemplary embodiment of the present application, and the apparatus includes:
人体生理数据获取模块701,用于基于可穿戴式设备中传感器采集到的传感器数据确定人体生理数据;A human physiological data acquisition module 701, configured to determine human physiological data based on sensor data collected by sensors in the wearable device;
音频数据采集模块702,用于响应于人体生理数据满足第一条件,通过麦克风进行音频采集,得到音频数据;An audio data collection module 702, configured to perform audio collection through a microphone in response to the human physiological data satisfying the first condition to obtain audio data;
触发模块703,用于响应于音频数据满足第二条件,触发紧急求助功能。The triggering module 703 is configured to trigger the emergency help function in response to the audio data meeting the second condition.
可选的,触发模块703,包括:Optionally, the trigger module 703 includes:
音频分离单元,用于对音频数据进行音频分离,得到人声音频数据和环境声音频数据;The audio separation unit is used for audio separation of audio data to obtain human voice audio data and ambient sound audio data;
人声识别单元,用于对人声音频数据进行识别,得到人声识别结果;The human voice recognition unit is used to identify the human voice audio data to obtain the human voice recognition result;
环境声识别单元,用于对环境声音频数据进行识别,得到环境声识别结果;The environmental sound recognition unit is used to recognize the environmental sound audio data to obtain the environmental sound recognition result;
触发单元,用于响应于人声识别结果和/或环境声识别结果指示音频数据满足第二条件,触发紧急求助功能。A triggering unit, configured to trigger the emergency help function in response to the human voice recognition result and/or the ambient sound recognition result indicating that the audio data satisfies the second condition.
可选的,人声识别单元,用于:Optional, voice recognition unit for:
对人声音频数据进行情绪识别,得到人声情绪信息;Perform emotion recognition on vocal audio data to obtain vocal emotional information;
对人声音频数据进行音频文本转换,得到人声文本;对人声文本进行关键词匹配,得到关键词匹配结果,关键词匹配结果用于指示人声文本中是否包含预设关键词;Perform audio-to-text conversion on the human voice audio data to obtain human voice text; perform keyword matching on the human voice text to obtain a keyword matching result, and the keyword matching result is used to indicate whether the human voice text contains preset keywords;
将人声情绪信息和/或关键词匹配结果确定为人声识别结果;Determine the human voice emotion information and/or the keyword matching result as the human voice recognition result;
可选的,环境声识别单元,用于:Optional, ambient sound recognition unit for:
对环境声音频数据进行环境识别,得到环境信息,并将环境信息确定为环境声识别结果,环境信息用于表征当前所处环境的环境类型。The environmental sound audio data is subjected to environmental recognition to obtain environmental information, and the environmental information is determined as the environmental sound recognition result, and the environmental information is used to represent the environmental type of the current environment.
可选的,触发单元,还用于:Optionally, the trigger unit is also used to:
响应于人声情绪信息指示预设情绪,和/或关键词匹配结果指示人声文本中包含预设关键词,和/或环境信息指示处于安静环境,确定音频数据满足第二条件,并触发紧急求助功能。In response to the vocal emotion information indicating a preset emotion, and/or the keyword matching result indicating that the vocal text contains a preset keyword, and/or the environment information indicating a quiet environment, determine that the audio data satisfies the second condition, and trigger an emergency Help function.
可选的,触发单元,还用于:Optionally, the trigger unit is also used to:
响应于环境信息指示处于安静环境,获取当前时间;In response to the environment information indicating that the environment is in a quiet environment, obtain the current time;
响应于当前时间位于预设时段,确定音频数据满足第二条件,并触发紧急求助功能。In response to the current time being within the preset time period, it is determined that the audio data satisfies the second condition, and the emergency help function is triggered.
可选的,音频数据采集模块702,包括:Optionally, the audio data collection module 702 includes:
波动幅度确定单元,用于基于连续的人体生理数据,确定人体生理数据的波动幅度;The fluctuation range determination unit is used for determining the fluctuation range of the human physiological data based on the continuous human physiological data;
音频采集单元,用于响应于波动幅度大于幅度阈值,确定人体生理数据满足第一条件,并通过麦克风进行音频采集,得到音频数据。The audio collection unit is used for determining that the physiological data of the human body meets the first condition in response to the fluctuation amplitude being greater than the amplitude threshold, and performing audio collection through a microphone to obtain audio data.
可选的,人体生理数据包括心率数据和压力数据中的至少一种;Optionally, the human physiological data includes at least one of heart rate data and stress data;
波动幅度包括心率波动幅度和压力波动幅度中的至少一种。The fluctuation range includes at least one of a heart rate fluctuation range and a pressure fluctuation range.
可选的,该装置还包括:Optionally, the device further includes:
风险提示模块,用于响应于人体生理数据满足第一条件,进行风险提示;a risk prompting module, configured to perform risk prompting in response to the human physiological data satisfying the first condition;
可选的,触发模块703,还用于:Optionally, the triggering module 703 is further configured to:
响应于音频数据满足第二条件,且未接收到对风险提示的正面反馈,触发紧急求助功能,正面反馈用于指示人体生理数据正常。In response to the audio data meeting the second condition and no positive feedback on the risk prompt being received, an emergency help function is triggered, and the positive feedback is used to indicate that the human physiological data is normal.
可选的,触发模块703,还用于:Optionally, the triggering module 703 is further configured to:
向预设紧急联系人发送求助信息或发起紧急通讯,求助信息中包含音频数据和地理位置信息。Send a help message or initiate an emergency communication to the preset emergency contact. The help message includes audio data and geographic location information.
综上所述,本申请实施例提供的紧急求助功能的触发方法,基于可穿戴式设备内的传感器实时监测人体生理数据,当监测到人体生理数据满足第一条件时,即人体生理数据发生异常,判断用户可能出现紧急状况,从而通过麦克风采集外界音频数据,并对音频数据进行分析,进而在音频数据满足第二条件时,确定用户处于紧急求助状态,并触发紧急求助功能;采用本申请实施例提供的方法,基于人体生理数据和音频数据进行紧急求助状态识别,能够在用户无法手动触发紧急求助功能的情况下实现紧急求助功能的自动触发,提高了紧急求助功能的触发及时性;同时,以人体生理数据和音频数据作为触发依据,有助于降低误触发概率,提高触发时机的准确性。To sum up, the method for triggering the emergency help function provided by the embodiment of the present application is based on the real-time monitoring of human physiological data based on the sensors in the wearable device. When the monitored human physiological data meets the first condition, that is, the human physiological data is abnormal. , judging that the user may be in an emergency situation, so as to collect external audio data through the microphone, and analyze the audio data, and then when the audio data meets the second condition, determine that the user is in an emergency state of assistance, and trigger the emergency assistance function; The method provided by the example, based on human physiological data and audio data for emergency help state identification, can realize the automatic triggering of the emergency help function when the user cannot manually trigger the emergency help function, and improve the triggering timeliness of the emergency help function; at the same time, Using human physiological data and audio data as the trigger basis can help reduce the probability of false triggering and improve the accuracy of trigger timing.
请参考图8,其示出了本申请一个示例性实施例提供的终端的结构方框图。该终端800可以是智能手机、平板电脑、可穿戴式设备等。本申请中的终端800可以包括一个或多个如下部件:处理器810和存储器820。Please refer to FIG. 8 , which shows a structural block diagram of a terminal provided by an exemplary embodiment of the present application. The terminal 800 may be a smart phone, a tablet computer, a wearable device, or the like. The terminal 800 in this application may include one or more of the following components: a processor 810 and a memory 820 .
处理器810可以包括一个或者多个处理核心。处理器810利用各种接口和线路连接整个终端800内的各个部分,通过运行或执行存储在存储器820内的指令、程序、代码集或指令集,以及调用存储在存储器820内的数据,执行终端的各种功能和处理数据。可选地,处理器810可以采用数字信号处理(Digital Signal Processing,DSP)、现场可编程门阵列(Field-Programmable Gate Array, FPGA)、可编程逻辑阵列(Programmable Logic Array,PLA)中的至少一种硬件形式来实现。处理器810可集成中央处理器(Central Processing Unit,CPU)、图像处理器(Graphics Processing Unit,GPU)、神经网络处理器(Neural-network Processing Unit,NPU)和调制解调器等中的一种或几种的组合。其中,CPU主要处理操作***、用户界面和应用程序等;GPU用于负责触摸显示屏830所需要显示的内容的渲染和绘制;NPU用于实现人工智能(Artificial Intelligence,AI)功能;调制解调器用于处理无线通信。可以理解的是,上述调制解调器也可以不集成到处理器810中,单独通过一块芯片进行实现。 Processor 810 may include one or more processing cores. The processor 810 uses various interfaces and lines to connect various parts in the entire terminal 800, and executes the terminal by running or executing the instructions, programs, code sets or instruction sets stored in the memory 820, and calling the data stored in the memory 820. various functions and processing data. Optionally, the processor 810 may adopt at least one of digital signal processing (Digital Signal Processing, DSP), field-programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). A hardware form is implemented. The processor 810 may integrate one or more of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU), a neural network processor (Neural-network Processing Unit, NPU), and a modem, etc. The combination. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is used for rendering and drawing the content that needs to be displayed on the touch screen 830; the NPU is used for implementing artificial intelligence (Artificial Intelligence, AI) functions; the modem is used for Handle wireless communications. It can be understood that, the above-mentioned modem may not be integrated into the processor 810, but is implemented by a single chip.
存储器820可以包括随机存储器(Random Access Memory,RAM),也可以包括只读存储器(Read-Only Memory,ROM)。可选地,该存储器820包括非瞬时性计算机可读介质(non-transitory computer-readable storage medium)。存储器820可用于存储指令、程序、代码、代码集或指令集。存储器820可包括存储程序区和存储数据区,其中,存储程序区可存储用于实现操作***的指令、用于至少一个功能的指令(比如触控功能、声音播放功能、图像播放功能等)、用于实现下述各个方法实施例的指令等;存储数据区可存储根据终端800的使用所创建的数据(比如音频数据、电话本)等。The memory 820 may include a random access memory (Random Access Memory, RAM), or may include a read-only memory (Read-Only Memory, ROM). Optionally, the memory 820 includes a non-transitory computer-readable storage medium. Memory 820 may be used to store instructions, programs, codes, sets of codes, or sets of instructions. The memory 820 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), Instructions and the like for implementing the following various method embodiments; the storage data area may store data (such as audio data, phone book) and the like created according to the use of the terminal 800 .
本申请实施例中,终端800还可以包括用于监测人体生理情况的传感器830,该传感器830用于采集传感器数据,并将传感器数据发送至处理器810,由处理器810基于传感器数据得到用户的人体生理数据。其中,传感器830可以包括心率传感器、血氧传感器、皮肤电导传感器、皮肤温度传感器等等。In this embodiment of the present application, the terminal 800 may further include a sensor 830 for monitoring human physiological conditions, the sensor 830 is used to collect sensor data, and send the sensor data to the processor 810, and the processor 810 obtains the user's information based on the sensor data. Human Physiological Data. The sensor 830 may include a heart rate sensor, a blood oxygen sensor, a skin conductance sensor, a skin temperature sensor, and the like.
本申请实施例中,终端800还可以包括麦克风840,该麦克风840用于采集外界音频数据,并将音频数据发送至处理器810,由处理器810对音频数据进行分析处理。In this embodiment of the present application, the terminal 800 may further include a microphone 840, and the microphone 840 is used to collect external audio data, and send the audio data to the processor 810, and the processor 810 analyzes and processes the audio data.
除此之外,本领域技术人员可以理解,上述附图所示出的终端800的结构并不构成对终端800的限定,终端可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。比如,终端800中还包括显示屏、射频电路、无线保真(Wireless Fidelity,WiFi)组件、电源、蓝牙组件等部件,在此不再赘述。In addition, those skilled in the art can understand that the structure of the terminal 800 shown in the above drawings does not constitute a limitation on the terminal 800, and the terminal may include more or less components than those shown in the drawings, or a combination of some components, or a different arrangement of components. For example, the terminal 800 further includes components such as a display screen, a radio frequency circuit, a wireless fidelity (Wireless Fidelity, WiFi) component, a power supply, and a Bluetooth component, which will not be repeated here.
本申请实施例还提供了一种计算机可读存储介质,存储介质中存储有至少一条指令,所述至少一条指令由处理器加载并执行以实现如上各个实施例所述的紧急求助功能的触发方法。Embodiments of the present application further provide a computer-readable storage medium, where at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement the method for triggering the emergency help function described in the above embodiments .
本申请实施例提供了还一种计算机程序产品或计算机程序,该计算机程序产品或计算机程序包括计算机指令,该计算机指令存储在计算机可读存储介质中。终端的处理器从计算机可读存储介质读取该计算机指令,处理器执行该计算机指令,使得该终端执行上述方面的各种可选实现方式中提供的紧急求助功能的触发方法。Embodiments of the present application provide yet another computer program product or computer program, where the computer program product or computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the terminal reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the terminal executes the method for triggering the emergency help function provided in various optional implementation manners of the foregoing aspects.
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过 硬件来完成,也可以通过程序来指令相关的硬件完成,所述的程序可以存储于一种计算机可读存储介质中,上述提到的存储介质可以是只读存储器,磁盘或光盘等。Those of ordinary skill in the art can understand that all or part of the steps of implementing the above embodiments can be completed by hardware, or can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The storage medium mentioned may be a read-only memory, a magnetic disk or an optical disk, etc.
以上仅为本申请的可选实施例,并不用以限制本申请,凡在本申请的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本申请的保护范围之内。The above are only optional embodiments of the present application, and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application. Inside.
Claims (21)
- 一种紧急求助功能的触发方法,所述方法包括:A method for triggering an emergency help function, the method comprising:基于可穿戴式设备中传感器采集到的传感器数据确定人体生理数据;Determine human physiological data based on sensor data collected by sensors in the wearable device;响应于所述用人体理数据满足第一条件,通过麦克风进行音频采集,得到音频数据;In response to the user's physical data meeting the first condition, audio collection is performed through a microphone to obtain audio data;响应于所述音频数据满足第二条件,触发紧急求助功能。In response to the audio data satisfying the second condition, an emergency assistance function is triggered.
- 根据权利要求1所述的方法,其中,所述响应于所述音频数据满足第二条件,触发紧急求助功能,包括:The method of claim 1, wherein triggering an emergency assistance function in response to the audio data meeting a second condition comprises:对所述音频数据进行音频分离,得到人声音频数据和环境声音频数据;Audio separation is performed on the audio data to obtain human voice audio data and ambient sound audio data;对所述人声音频数据进行识别,得到人声识别结果;Identifying the voice audio data to obtain a voice recognition result;对所述环境声音频数据进行识别,得到环境声识别结果;Identifying the ambient sound audio data to obtain an ambient sound identification result;响应于所述人声识别结果和/或所述环境声识别结果指示所述音频数据满足所述第二条件,触发紧急求助功能。An emergency help function is triggered in response to the human voice recognition result and/or the ambient sound recognition result indicating that the audio data satisfies the second condition.
- 根据权利要求2所述的方法,其中,所述对所述人声音频数据进行识别,得到人声识别结果,包括:The method according to claim 2, wherein the identifying the human voice audio data to obtain a human voice recognition result comprises:对所述人声音频数据进行情绪识别,得到人声情绪信息;Perform emotion recognition on the vocal audio data to obtain vocal emotion information;对所述人声音频数据进行音频文本转换,得到人声文本;对所述人声文本进行关键词匹配,得到关键词匹配结果,所述关键词匹配结果用于指示所述人声文本中是否包含预设关键词;Perform audio-text conversion on the vocal audio data to obtain vocal text; perform keyword matching on the vocal text to obtain a keyword matching result, and the keyword matching result is used to indicate whether the vocal text is contains preset keywords;将所述人声情绪信息和/或所述关键词匹配结果确定为所述人声识别结果;Determining the human voice emotion information and/or the keyword matching result as the human voice recognition result;所述对所述环境声音频数据进行识别,得到环境声识别结果,包括:The described ambient sound audio data is identified to obtain an ambient sound identification result, including:对所述环境声音频数据进行环境识别,得到环境信息,并将所述环境信息确定为所述环境声识别结果,所述环境信息用于表征当前所处环境的环境类型。Perform environmental recognition on the environmental sound audio data to obtain environmental information, and determine the environmental information as the environmental sound recognition result, where the environmental information is used to represent the environmental type of the current environment.
- 根据权利要求3所述的方法,其中,所述响应于所述人声识别结果和/或所述环境声识别结果指示所述音频数据满足所述第二条件,触发紧急求助功能,包括:The method according to claim 3, wherein, in response to the human voice recognition result and/or the ambient sound recognition result indicating that the audio data meets the second condition, triggering an emergency help function comprises:响应于所述人声情绪信息指示预设情绪,和/或所述关键词匹配结果指示所述人声文本中包含所述预设关键词,和/或所述环境信息指示处于安静环境,确定所述音频数据满足所述第二条件,触发紧急求助功能。In response to the vocal emotion information indicating a preset emotion, and/or the keyword matching result indicating that the human voice text contains the preset keyword, and/or the environment information indicating that it is in a quiet environment, determine The audio data satisfies the second condition, triggering an emergency help function.
- 根据权利要求4所述的方法,其中,所述响应于所述环境信息指示处于安静环境,确定所述音频数据满足所述第二条件,触发紧急求助功能,包括:The method according to claim 4, wherein the determining that the audio data meets the second condition in response to the environment information indicating that the environment is in a quiet environment, and triggering an emergency help function, comprises:响应于所述环境信息指示处于安静环境,获取当前时间;obtaining the current time in response to the environment information indicating that the environment is in a quiet environment;响应于所述当前时间位于预设时段,确定所述音频数据满足所述第二条件,并触发紧急求助功能。In response to the current time being within a preset time period, it is determined that the audio data satisfies the second condition, and an emergency help function is triggered.
- 根据权利要求1至5任一所述的方法,其中,所述响应于所述人体生理数据满足第一条件,通过麦克风进行音频采集,得到音频数据,包括:The method according to any one of claims 1 to 5, wherein, in response to the human physiological data satisfying the first condition, performing audio collection through a microphone to obtain audio data, comprising:基于连续的所述人体生理数据,确定所述人体生理数据的波动幅度;determining the fluctuation range of the human physiological data based on the continuous human physiological data;响应于所述波动幅度大于幅度阈值,确定所述人体生理数据满足所述第一条件,并通过所述麦克风进行音频采集,得到所述音频数据。In response to the fluctuation amplitude being greater than the amplitude threshold, it is determined that the human physiological data satisfies the first condition, and audio is collected through the microphone to obtain the audio data.
- 根据权利要求6所述的方法,其中,The method of claim 6, wherein,所述人体生理数据包括心率数据和压力数据中的至少一种;The human physiological data includes at least one of heart rate data and stress data;所述波动幅度包括心率波动幅度和压力波动幅度中的至少一种。The fluctuation range includes at least one of a heart rate fluctuation range and a pressure fluctuation range.
- 根据权利要求1至5任一所述的方法,其中,所述基于可穿戴式设备中传感器采集到的传感器数据确定人体生理数据之后,所述方法还包括:The method according to any one of claims 1 to 5, wherein after determining the human physiological data based on the sensor data collected by the sensors in the wearable device, the method further comprises:响应于所述人体生理数据满足所述第一条件,进行风险提示;In response to the human physiological data meeting the first condition, perform a risk prompt;所述响应于所述音频数据满足第二条件,触发紧急求助功能,包括:The triggering an emergency help function in response to the audio data meeting the second condition includes:响应于所述音频数据满足所述第二条件,且未接收到对风险提示的正面反馈,触发紧急求助功能,所述正面反馈用于指示所述人体生理数据正常。In response to the audio data meeting the second condition and no positive feedback on the risk prompt is received, an emergency help function is triggered, and the positive feedback is used to indicate that the human physiological data is normal.
- 根据权利要求1至5任一所述的方法,其中,所述触发紧急求助功能,包括:The method according to any one of claims 1 to 5, wherein the triggering an emergency assistance function comprises:向预设紧急联系人发送求助信息或发起紧急通讯,所述求助信息中包含所述音频数据和地理位置信息。Send help information to a preset emergency contact or initiate emergency communication, where the help information includes the audio data and geographic location information.
- 一种紧急求助功能的触发装置,所述装置包括:A triggering device for emergency help function, the device includes:人体生理数据采集模块,用于基于可穿戴式设备中传感器采集到的传感器数据确定人体生理数据;The human body physiological data acquisition module is used to determine the human body physiological data based on the sensor data collected by the sensors in the wearable device;音频数据采集模块,用于响应于所述人体生理数据满足第一条件,通过麦克风进行音频采集,得到音频数据;an audio data acquisition module, configured to perform audio acquisition through a microphone in response to the human physiological data satisfying the first condition to obtain audio data;触发模块,用于响应于所述音频数据满足第二条件,触发紧急求助功能。A triggering module, configured to trigger an emergency help function in response to the audio data meeting the second condition.
- 根据权利要求10所述的装置,其中,所述触发模块,包括:The apparatus according to claim 10, wherein the triggering module comprises:音频分离单元,用于对所述音频数据进行音频分离,得到人声音频数据和环境声音频数据;an audio separation unit, for performing audio separation on the audio data to obtain human voice audio data and ambient sound audio data;人声识别单元,用于对所述人声音频数据进行识别,得到人声识别结果;A voice recognition unit, used for identifying the voice audio data to obtain a voice recognition result;环境声识别单元,用于对所述环境声音频数据进行识别,得到环境声识别结果;an environmental sound recognition unit, used for identifying the environmental sound audio data to obtain an environmental sound recognition result;触发单元,用于响应于所述人声识别结果和/或所述环境声识别结果指示所述音频数据满足所述第二条件,触发紧急求助功能。A triggering unit, configured to trigger an emergency help function in response to the human voice recognition result and/or the ambient sound recognition result indicating that the audio data satisfies the second condition.
- 根据权利要求11所述的装置,其中,所述人声识别单元,用于:The device according to claim 11, wherein the human voice recognition unit is used for:对所述人声音频数据进行情绪识别,得到人声情绪信息;Perform emotion recognition on the vocal audio data to obtain vocal emotion information;对所述人声音频数据进行音频文本转换,得到人声文本;对所述人声文本进行关键词匹配,得到关键词匹配结果,所述关键词匹配结果用于指示所述人声文本中是否包含预设关键词;Perform audio-text conversion on the voice audio data to obtain voice text; perform keyword matching on the voice text to obtain a keyword matching result, and the keyword matching result is used to indicate whether the voice text is in the voice text. contains preset keywords;将所述人声情绪信息和/或所述关键词匹配结果确定为所述人声识别结果;Determining the human voice emotion information and/or the keyword matching result as the human voice recognition result;所述环境声识别单元,用于:The ambient sound recognition unit is used for:对所述环境声音频数据进行环境识别,得到环境信息,并将所述环境信息确定为所述环境声识别结果,所述环境信息用于表征当前所处环境的环境类型。Perform environmental recognition on the environmental sound audio data to obtain environmental information, and determine the environmental information as the environmental sound recognition result, where the environmental information is used to represent the environmental type of the current environment.
- 根据权利要求12所述的装置,其中,所述触发单元,还用于:The device according to claim 12, wherein the trigger unit is further configured to:响应于所述人声情绪信息指示预设情绪,和/或所述关键词匹配结果指示所述人声文本中包含所述预设关键词,和/或所述环境信息指示处于安静环境,确定所述音频数据满足所述第二条件,触发紧急求助功能。In response to the vocal emotion information indicating a preset emotion, and/or the keyword matching result indicating that the human voice text contains the preset keyword, and/or the environment information indicating that it is in a quiet environment, determine The audio data satisfies the second condition, triggering an emergency help function.
- 根据权利要求13所述的装置,其中,所述触发单元,还用于:The device according to claim 13, wherein the trigger unit is further configured to:响应于所述环境信息指示处于安静环境,获取当前时间;obtaining the current time in response to the environment information indicating that the environment is in a quiet environment;响应于所述当前时间位于预设时段,确定所述音频数据满足所述第二条件,并触发紧急求助功能。In response to the current time being within a preset time period, it is determined that the audio data satisfies the second condition, and an emergency help function is triggered.
- 根据权利要求10至14任一所述的装置,其中,所述音频数据采集模块,包括:The device according to any one of claims 10 to 14, wherein the audio data acquisition module comprises:波动幅度确定单元,用于基于连续的所述人体生理数据,确定所述人体生理数据的波动幅度;a fluctuation range determination unit, configured to determine the fluctuation range of the human physiological data based on the continuous human physiological data;音频采集单元,用于响应于所述波动幅度大于幅度阈值,确定所述人体生理数据满足所述第一条件,并通过所述麦克风进行音频采集,得到所述音频数据。An audio collection unit, configured to determine that the human physiological data meets the first condition in response to the fluctuation amplitude being greater than an amplitude threshold, and perform audio collection through the microphone to obtain the audio data.
- 根据权利要求15所述的装置,其中,The apparatus of claim 15, wherein,所述人体生理数据包括心率数据和压力数据中的至少一种;The human physiological data includes at least one of heart rate data and stress data;所述波动幅度包括心率波动幅度和压力波动幅度中的至少一种。The fluctuation range includes at least one of a heart rate fluctuation range and a pressure fluctuation range.
- 根据权利要求10至14任一所述的装置,其中,所述装置还包括:The apparatus of any one of claims 10 to 14, wherein the apparatus further comprises:风险提示模块,用于响应于所述人体生理数据满足所述第一条件,进行风险提示;a risk prompting module, configured to perform risk prompting in response to the human physiological data meeting the first condition;所述触发模块,还用于:The trigger module is also used for:响应于所述音频数据满足所述第二条件,且未接收到对风险提示的正面反馈,触发紧急求助功能,所述正面反馈用于指示所述人体生理数据正常。In response to the audio data meeting the second condition and no positive feedback on the risk prompt is received, an emergency help function is triggered, and the positive feedback is used to indicate that the human physiological data is normal.
- 根据权利要求10至14任一所述的装置,其中,所述触发模块,还用于:The device according to any one of claims 10 to 14, wherein the trigger module is further configured to:向预设紧急联系人发送求助信息或发起紧急通讯,所述求助信息中包含所述音频数据和地理位置信息。Send help information to a preset emergency contact or initiate emergency communication, where the help information includes the audio data and geographic location information.
- 一种终端,其特征在于,所述终端包括处理器和存储器;所述存储器存储有至少一条指令,所述至少一条指令用于被所述处理器执行以实现如权利要求1至9任一所述的紧急求助功能的触发方法。A terminal, characterized in that the terminal includes a processor and a memory; the memory stores at least one instruction, and the at least one instruction is used to be executed by the processor to implement any one of claims 1 to 9. The trigger method of the emergency help function described above.
- 一种计算机可读存储介质,其特征在于,所述存储介质存储有至少一条指令,所述至少一条指令用于被处理器执行以实现如权利要求1至9任一所述的紧急求助功能的触发方法。A computer-readable storage medium, characterized in that the storage medium stores at least one instruction, and the at least one instruction is used to be executed by a processor to implement the emergency assistance function according to any one of claims 1 to 9. trigger method.
- 一种计算机程序产品或计算机程序,所述计算机程序产品或计算机程序包括计算机指令,所述计算机指令存储在计算机可读存储介质中,处理器从所述计算机可读存储介质读取并执行所述计算机指令,以实现如权利要求1至9任一所述的紧急求助功能的触发方法。A computer program product or computer program comprising computer instructions stored in a computer-readable storage medium from which a processor reads and executes the The computer instructions are used to realize the triggering method of the emergency assistance function according to any one of claims 1 to 9.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110118932.6 | 2021-01-28 | ||
CN202110118932.6A CN114821962B (en) | 2021-01-28 | 2021-01-28 | Triggering method, triggering device, triggering terminal and storage medium for emergency help function |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022160938A1 true WO2022160938A1 (en) | 2022-08-04 |
Family
ID=82526838
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/135473 WO2022160938A1 (en) | 2021-01-28 | 2021-12-03 | Emergency help-seeking function triggering method and apparatus, terminal, and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN114821962B (en) |
WO (1) | WO2022160938A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116318218A (en) * | 2023-03-13 | 2023-06-23 | 武汉理工大学 | Communication device for individual travel of mental disorder teenagers |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107049280A (en) * | 2017-05-23 | 2017-08-18 | 宁波大学 | A kind of intelligent wearable device of mobile Internet |
CN108694808A (en) * | 2018-05-25 | 2018-10-23 | 合肥尚强电气科技有限公司 | Multi-channel taxi driver personal safety intelligent analysis alarm method and system |
CN108711256A (en) * | 2018-05-25 | 2018-10-26 | 合肥博之泰电子科技有限公司 | The energy saving intellectual analysis of the personal safety by all kinds of means alarm method of one kind and system |
US20190156191A1 (en) * | 2017-11-17 | 2019-05-23 | International Business Machines Corporation | Detecting personal danger using a deep learning system |
CN110459219A (en) * | 2019-08-26 | 2019-11-15 | 恒大智慧科技有限公司 | A kind of danger warning method, apparatus, computer equipment and storage medium |
CN209883226U (en) * | 2018-12-04 | 2020-01-03 | 山西大学 | Intelligent bracelet capable of sending multi-mode distress message |
CN111445664A (en) * | 2020-04-15 | 2020-07-24 | 杭州奥美健康科技有限公司 | Distress alarm method and device based on keyword 'lifesaving o' and application |
CN111491286A (en) * | 2020-04-07 | 2020-08-04 | 惠州Tcl移动通信有限公司 | Emergency rescue method, device and terminal |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102546954A (en) * | 2011-08-29 | 2012-07-04 | 赵永频 | Security robot phone |
CN104240438A (en) * | 2014-09-01 | 2014-12-24 | 百度在线网络技术(北京)有限公司 | Method and device for achieving automatic alarming through mobile terminal and mobile terminal |
JP2020099367A (en) * | 2017-03-28 | 2020-07-02 | 株式会社Seltech | Emotion recognition device and emotion recognition program |
CN106991790A (en) * | 2017-05-27 | 2017-07-28 | 重庆大学 | Old man based on multimode signature analysis falls down method of real-time and system |
CN108682118A (en) * | 2018-05-25 | 2018-10-19 | 合肥择浚电气设备有限公司 | It is a kind of the person state of emergency under automatically analyze alarm method and system |
CN108961667A (en) * | 2018-05-25 | 2018-12-07 | 合肥佳洋电子科技有限公司 | Alarm method and system are automatically analyzed under a kind of personal state of emergency of energy conservation |
CN111243224A (en) * | 2018-11-09 | 2020-06-05 | 北京搜狗科技发展有限公司 | Method and device for realizing alarm |
EP3986275A4 (en) * | 2019-06-20 | 2022-11-30 | HB Innovations, Inc. | System and method for monitoring/detecting and responding to infant breathing |
CN210924846U (en) * | 2019-08-21 | 2020-07-03 | 深圳市三五智能科技有限公司 | Multi-functional baby's alarm of wearing formula |
-
2021
- 2021-01-28 CN CN202110118932.6A patent/CN114821962B/en active Active
- 2021-12-03 WO PCT/CN2021/135473 patent/WO2022160938A1/en active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107049280A (en) * | 2017-05-23 | 2017-08-18 | 宁波大学 | A kind of intelligent wearable device of mobile Internet |
US20190156191A1 (en) * | 2017-11-17 | 2019-05-23 | International Business Machines Corporation | Detecting personal danger using a deep learning system |
CN108694808A (en) * | 2018-05-25 | 2018-10-23 | 合肥尚强电气科技有限公司 | Multi-channel taxi driver personal safety intelligent analysis alarm method and system |
CN108711256A (en) * | 2018-05-25 | 2018-10-26 | 合肥博之泰电子科技有限公司 | The energy saving intellectual analysis of the personal safety by all kinds of means alarm method of one kind and system |
CN209883226U (en) * | 2018-12-04 | 2020-01-03 | 山西大学 | Intelligent bracelet capable of sending multi-mode distress message |
CN110459219A (en) * | 2019-08-26 | 2019-11-15 | 恒大智慧科技有限公司 | A kind of danger warning method, apparatus, computer equipment and storage medium |
CN111491286A (en) * | 2020-04-07 | 2020-08-04 | 惠州Tcl移动通信有限公司 | Emergency rescue method, device and terminal |
CN111445664A (en) * | 2020-04-15 | 2020-07-24 | 杭州奥美健康科技有限公司 | Distress alarm method and device based on keyword 'lifesaving o' and application |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116318218A (en) * | 2023-03-13 | 2023-06-23 | 武汉理工大学 | Communication device for individual travel of mental disorder teenagers |
Also Published As
Publication number | Publication date |
---|---|
CN114821962A (en) | 2022-07-29 |
CN114821962B (en) | 2023-10-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2713881B1 (en) | Method and system for assisting patients | |
US20200058208A1 (en) | Human voice feedback system | |
KR101840644B1 (en) | System of body gard emotion cognitive-based, emotion cognitive device, image and sensor controlling appararus, self protection management appararus and method for controlling the same | |
US20130211826A1 (en) | Audio Signals as Buffered Streams of Audio Signals and Metadata | |
WO2018076615A1 (en) | Information transmitting method and apparatus | |
CN113454710A (en) | System for evaluating sound presentation | |
CN110875032A (en) | Voice interaction system, voice interaction method, program, learning model generation device, and learning model generation method | |
WO2016183961A1 (en) | Method, system and device for switching interface of smart device, and nonvolatile computer storage medium | |
KR20190136706A (en) | Apparatus and method for predicting/recognizing occurrence of personal concerned context | |
WO2022160938A1 (en) | Emergency help-seeking function triggering method and apparatus, terminal, and storage medium | |
KR101504699B1 (en) | Phonetic conversation method and device using wired and wiress communication | |
CN110587621B (en) | Robot, robot-based patient care method, and readable storage medium | |
JP3233390U (en) | Notification device and wearable device | |
US20210224828A1 (en) | Real-time dynamic monitoring of sentiment trends and mitigation of the same in a live setting | |
JP6943490B1 (en) | Watching support device, watching support system, watching support method and program | |
CN112672120B (en) | Projector with voice analysis function and personal health data generation method | |
EP3793275B1 (en) | Location reminder method and apparatus, storage medium, and electronic device | |
JP2019060921A (en) | Information processor and program | |
TW202347096A (en) | Smart glass interface for impaired users or users with disabilities | |
US11917092B2 (en) | Systems and methods for detecting voice commands to generate a peer-to-peer communication link | |
CN105631224B (en) | Health monitoring method, mobile terminal and health monitoring system | |
CN113744896A (en) | Method for detecting user emotion, cloud server and terminal equipment | |
WO2021122136A1 (en) | Device, system and method for monitoring of a subject | |
CN112433602A (en) | Information processing apparatus, storage medium, and information processing method | |
Bellodi et al. | Dialogue support for memory impaired people |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21922528 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21922528 Country of ref document: EP Kind code of ref document: A1 |